Education in the new era advocates taking students as the main body and improving students’core literacy on this basis.Subjectivity has also become one of the keys to quality education.Primary school is not only the ...Education in the new era advocates taking students as the main body and improving students’core literacy on this basis.Subjectivity has also become one of the keys to quality education.Primary school is not only the initial stage of life,but also the key period to develop students’subjectivity.At present,there are many problems in class activities,such as the weak concept of taking students as the main body,the lack of subject consciousness among students,the flawed construction system of class activities,the unreasonable evaluation system of class activities,and so on.By establishing the role-playing model under the background of“class activity month,”students can play different roles in class activities and participate in various links,such as theme selection,scheme design,organization,implementation,summary,and evaluation of class activities.Through this process,it does not only improve the quality of class activities,but also cultivate students’subject consciousness and ability in a certain subject,thus highlighting their subject status in class activities.展开更多
In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can...In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.展开更多
Interest is the precondition and motivation for people's accomplishment.However,due to the exam-oriented system,millions of parents and teachers neglect the interests of children,and our children nearly forget the...Interest is the precondition and motivation for people's accomplishment.However,due to the exam-oriented system,millions of parents and teachers neglect the interests of children,and our children nearly forget their interests or hobbies.Based on different interests of children,the thesis analyzes how to apply the goal-setting theory in the second classroom teaching activities of College English,using the example of Lushan College of Guangxi University of Technology.展开更多
The shear wave(S-wave)velocity is a critical rock elastic parameter in shale reservoirs,especially for evaluating shale fracability.To effectively supplement S-wave velocity under the condition of no actual measuremen...The shear wave(S-wave)velocity is a critical rock elastic parameter in shale reservoirs,especially for evaluating shale fracability.To effectively supplement S-wave velocity under the condition of no actual measurement data,this paper proposes a physically-data driven method for the S-wave velocity prediction in shale reservoirs based on the class activation mapping(CAM)technique combined with a physically constrained two-dimensional Convolutional Neural Network(2D-CNN).High-sensitivity log curves related to S-wave velocity are selected as the basis from the data sensitivity analysis.Then,we establish a petrophysical model of complex multi-mineral components based on the petrophysical properties of porous medium and the Biot-Gassmann equation.This model can help reduce the dispersion effect and constrain the 2D-CNN.In deep learning,the 2D-CNN model is optimized using the Adam,and the class activation maps(CAMs)are obtained by replacing the fully connected layer with the global average pooling(GAP)layer,resulting in explainable results.The model is then applied to wells A,B1,and B2 in the southern Songliao Basin,China and compared with the unconstrained model and the petrophysical model.The results show higher prediction accuracy and generalization ability,as evidenced by correlation coefficients and relative errors of 0.98 and 2.14%,0.97 and 2.35%,0.96 and 2.89%in the three test wells,respectively.Finally,we present the defined C-factor as a means of evaluating the extent of concern regarding CAMs in regression problems.When the results of the petrophysical model are added to the 2D feature maps,the C-factor values are significantly increased,indicating that the focus of 2D-CNN can be significantly enhanced by incorporating the petrophysical model,thereby imposing physical constraints on the 2D-CNN.In addition,we establish the SHAP model,and the results of the petrophysical model have the highest average SHAP values across the three test wells.This helps to assist in proving the importance of constraints.展开更多
The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gaine...The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.展开更多
Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however...Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however,the predicted results have uncertainty in providing accurate informa-tion to users because of the“black box”problem in the deep learning model.Therefore,this study proposes a visual explanation method to overcome the uncertainty limitation of CNN-based defect identification.The visual repre-sentative gradient-weights class activation mapping(Grad-CAM)method is adopted to provide visually explainable information.A visualizing evaluation index is proposed to quantitatively analyze visual representations;this index reflects a rough estimate of the concordance rate between the visualized heat map and intended defects.In addition,an ablation study,adopting three-branch combinations with the VGG16,is implemented to identify perfor-mance variations by visualizing predicted results.Experiments reveal that the proposed model,combined with hybrid pooling,batch normalization,and multi-attention modules,achieves the best performance with an accuracy of 97.77%,corresponding to an improvement of 2.49%compared with the baseline model.Consequently,this study demonstrates that reliable results from an automatic defect classification model can be provided to an inspector through the visual representation of the predicted results using CNN models.展开更多
COVID-19 is a growing problem worldwide with a high mortality rate.As a result,the World Health Organization(WHO)declared it a pandemic.In order to limit the spread of the disease,a fast and accurate diagnosis is requ...COVID-19 is a growing problem worldwide with a high mortality rate.As a result,the World Health Organization(WHO)declared it a pandemic.In order to limit the spread of the disease,a fast and accurate diagnosis is required.A reverse transcript polymerase chain reaction(RT-PCR)test is often used to detect the disease.However,since this test is time-consuming,a chest computed tomography(CT)or plain chest X-ray(CXR)is sometimes indicated.The value of automated diagnosis is that it saves time and money by minimizing human effort.Three significant contributions are made by our research.Its initial purpose is to use the essential finetuning methodology to test the action and efficiency of a variety of vision models,ranging from Inception to Neural Architecture Search(NAS)networks.Second,by plotting class activationmaps(CAMs)for individual networks and assessing classification efficiency with AUC-ROC curves,the behavior of these models is visually analyzed.Finally,stacked ensembles techniques were used to provide greater generalization by combining finetuned models with six ensemble neural networks.Using stacked ensembles,the generalization of the models improved.Furthermore,the ensemble model created by combining all of the finetuned networks obtained a state-of-the-art COVID-19 accuracy detection score of 99.17%.The precision and recall rates were 99.99%and 89.79%,respectively,highlighting the robustness of stacked ensembles.The proposed ensemble approach performed well in the classification of the COVID-19 lesions on CXR according to the experimental results.展开更多
The multi-media teaching method refers to using computer as a teaching assistant in the teaching Chinese as the second language （TCSL） class. The purpose of employing multi-media technology is to encourage students...The multi-media teaching method refers to using computer as a teaching assistant in the teaching Chinese as the second language （TCSL） class. The purpose of employing multi-media technology is to encourage students＇ class participation, giving them explicit and specific impression of abstract contents and cultivating their intuitive grasp of linguistic points. Based on the current study of usage of multi-media technology in class teaching, this paper attempts to investigate mainly on its positive influence of multi-media technology in teaching.展开更多
The statistical study of F2 layer critical frequency at Dakar station from 1971 to 1996 is carried out. This paper shows foF2 statistical diurnal for all geomagnetic activities and all seasons and that during solar ma...The statistical study of F2 layer critical frequency at Dakar station from 1971 to 1996 is carried out. This paper shows foF2 statistical diurnal for all geomagnetic activities and all seasons and that during solar maximum and minimum phases. It emerges that foF2 diurnal variation graphs at Dakar station exhibits the different types of foF2 profiles in African EIA regions. The type of profile depends on solar activity, season and solar phase. During solar minimum and under quiet time condition, data show?the signature of a strength electrojet that is coupled with intense counter electrojet in the afternoon. Under disturbed conditions,?mean intense electrojet is observed in winter?during fluctuating and recurrent activities. Intense counter electrojet is seen under fluctuating and shock activities in all seasons coupled with strength electrojet in autumn. In summer?and spring under all geomagnetic activity condition, there is intense counter electrojet. During solar maximum, in summer and spring there is no electrojet under geomagnetic activity conditions.?Winter shows a mean intense electrojet. Winter and autumn are marked by the signature of the reversal electric field.展开更多
Facial emotion recognition is an essential and important aspect of the field of human-machine interaction.Past research on facial emotion recognition focuses on the laboratory environment.However,it faces many challen...Facial emotion recognition is an essential and important aspect of the field of human-machine interaction.Past research on facial emotion recognition focuses on the laboratory environment.However,it faces many challenges in real-world conditions,i.e.,illumination changes,large pose variations and partial or full occlusions.Those challenges lead to different face areas with different degrees of sharpness and completeness.Inspired by this fact,we focus on the authenticity of predictions generated by different<emotion,region>pairs.For example,if only the mouth areas are available and the emotion classifier predicts happiness,then there is a question of how to judge the authenticity of predictions.This problem can be converted into the contribution of different face areas to different emotions.In this paper,we divide the whole face into six areas:nose areas,mouth areas,eyes areas,nose to mouth areas,nose to eyes areas and mouth to eyes areas.To obtain more convincing results,our experiments are conducted on three different databases:facial expression recognition+(FER+),real-world affective faces database(RAF-DB)and expression in-the-wild(ExpW)dataset.Through analysis of the classification accuracy,the confusion matrix and the class activation map(CAM),we can establish convincing results.To sum up,the contributions of this paper lie in two areas:1)We visualize concerned areas of human faces in emotion recognition;2)We analyze the contribution of different face areas to different emotions in real-world conditions through experimental analysis.Our findings can be combined with findings in psychology to promote the understanding of emotional expressions.展开更多
In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to obtain.Therefore,it makes sense to learn more information(knowledge)from ...In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to obtain.Therefore,it makes sense to learn more information(knowledge)from a small number of hard-to-get pixel-level annotated images to apply to different tasks to maximize their usefulness and save time and training costs.In this paper,using Pixel-Level Labeled Images forMulti-Task Learning(PLDMLT),we focus on grading the severity of fundus images for Diabetic Retinopathy(DR).This is because,for the segmentation task,there is a finely labeled mask,while the severity grading task is without classification labels.To this end,we propose a two-stage multi-label learning weakly supervised algorithm,which generates initial classification pseudo labels in the first stage and visualizes heat maps at all levels of severity using Grad-Cam to further provide medical interpretability for the classification task.A multitask model framework with U-net as the baseline is proposed in the second stage.A label update network is designed to alleviate the gradient balance between the classification and segmentation tasks.Extensive experimental results show that our PLDMLTmethod significantly outperforms other stateof-the-art methods in DR segmentation on two public datasets,achieving up to 98.897%segmentation accuracy.In addition,our method achieves comparable competitiveness with single-task fully supervised learning in the DR severity grading task.展开更多
Segmenting dark-field images of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray light interference. Fully supe...Segmenting dark-field images of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray light interference. Fully supervised semantic segmentation algorithms have achieved state-of-the-art performance but rely on a large number of pixel-level labels, which are time-consuming and labor-consuming to produce. LayerCAM, an advanced weakly supervised semantic segmentation algorithm, can generate pixel-accurate results using only image-level labels, but its scattered and partially underactivated class activation regions degrade segmentation performance. In this paper, we propose a weakly supervised semantic segmentation method, continuous gradient class activation mapping(CAM) and its nonlinear multiscale fusion(continuous gradient fusion CAM). The method redesigns backpropagating gradients and nonlinearly activates multiscale fused heatmaps to generate more fine-grained class activation maps with an appropriate activation degree for different damage site sizes. Experiments on our dataset show that the proposed method can achieve segmentation performance comparable to that of fully supervised algorithms.展开更多
Scene recognition is a fundamental task in computer vision,which generally includes three vital stages,namely feature extraction,feature transformation and classification.Early research mainly focuses on feature extra...Scene recognition is a fundamental task in computer vision,which generally includes three vital stages,namely feature extraction,feature transformation and classification.Early research mainly focuses on feature extraction,but with the rise of Convolutional Neural Networks(CNNs),more and more feature transformation methods are proposed based on CNN features.In this work,a novel feature transformation algorithm called Graph Encoded Local Discriminative Region Representation(GEDRR)is proposed to find discriminative local representations for scene images and explore the relationship between the discriminative regions.In addition,we propose a method using the multi-head attention module to enhance and fuse convolutional feature maps.Combining the two methods and the global representation,a scene recognition framework called Global and Graph Encoded Local Discriminative Region Representation(G2ELDR2)is proposed.The experimental results on three scene datasets demonstrate the effectiveness of our model,which outperforms many state-of-the-arts.展开更多
The most salient argument that needs to be addressed universally is Early Breast Cancer Detection(EBCD),which helps people live longer lives.The Computer-Aided Detection(CADs)/Computer-Aided Diagnosis(CADx)sys-tem is ...The most salient argument that needs to be addressed universally is Early Breast Cancer Detection(EBCD),which helps people live longer lives.The Computer-Aided Detection(CADs)/Computer-Aided Diagnosis(CADx)sys-tem is indeed a software automation tool developed to assist the health profes-sions in Breast Cancer Detection and Diagnosis(BCDD)and minimise mortality by the use of medical histopathological image classification in much less time.This paper purposes of examining the accuracy of the Convolutional Neural Network(CNN),which can be used to perceive breast malignancies for initial breast cancer detection to determine which strategy is efficient for the early iden-tification of breast cell malignancies formation of masses and Breast microcalci-fications on the mammogram.When we have insufficient data for a new domain that is desired to be handled by a pre-trained Convolutional Neural Network of Residual Network(ResNet50)for Breast Cancer Detection and Diagnosis,to obtain the Discriminative Localization,Convolutional Neural Network with Class Activation Map(CAM)has also been used to perform breast microcalcifications detection tofind a specific class in the Histopathological image.The test results indicate that this method performed almost 225.15%better at determining the exact location of disease(Discriminative Localization)through breast microcalci-fications images.ResNet50 seems to have the highest level of accuracy for images of Benign Tumour(BT)/Malignant Tumour(MT)cases at 97.11%.ResNet50’s average accuracy for pre-trained Convolutional Neural Network is 94.17%.展开更多
This paper proposes an accurate,efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network(CNN).The state-of-the-art robust CNN model(EfficientNet)is applie...This paper proposes an accurate,efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network(CNN).The state-of-the-art robust CNN model(EfficientNet)is applied to tunnel wall image recognition.Gaussian filtering,data augmentation and other data pre-processing techniques are used to improve the data quality and quantity.Combined with transfer learning,the generality,accuracy and efficiency of the deep learning(DL)model are further improved,and finally we achieve 89.96%accuracy.Compared with other state-of-the-art CNN architectures,such as ResNet and Inception-ResNet-V2(IRV2),the presented deep transfer learning model is more stable,accurate and efficient.To reveal the rock classification mechanism of the proposed model,Gradient-weight Class Activation Map(Grad-CAM)visualizations are integrated into the model to enable its explainability and accountability.The developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou,China,with great results.展开更多
In the teaching process of kindergarten teachers, curriculum activities such as creation and compilation of children's dance not only play a good role in promoting the optimization of students' knowledge struc...In the teaching process of kindergarten teachers, curriculum activities such as creation and compilation of children's dance not only play a good role in promoting the optimization of students' knowledge structure, but also can improve students' dance literacy, and improve students' innovative ability and comprehensive practical ability, which is also a prerequisite for their future growth as an excellent kindergarten teacher. This paper aims at the problems in the process of setting up dance creation course for children, analyzes the necessity of setting up this activity course, and finally puts forward several feasible measures to effectively carry out the activity course according to the current situation.展开更多
This study examines whether a group of captive false killer whales(P seudorca crassidens) showed variations in the vocal rate around feeding times. The high level of motivation to express appetitive behaviors in capti...This study examines whether a group of captive false killer whales(P seudorca crassidens) showed variations in the vocal rate around feeding times. The high level of motivation to express appetitive behaviors in captive animals may lead them to respond with changes of the behavioral activities during the time prior to food deliveries which are referred to as food anticipatory activity. False killer whales at Qingdao Polar Ocean World(Qingdao, China) showed signifi cant variations of the rates of both the total sounds and sound classes(whistles, clicks, and burst pulses) around feedings. Precisely, from the Transition interval that recorded the lowest vocalization rate(3.40 s/m/d), the whales increased their acoustic emissions upon trainers' arrival(13.08 s/m/d). The high rate was maintained or intensifi ed throughout the food delivery(25.12 s/m/d), and then reduced immediately after the animals were fed(9.91 s/m/d). These changes in the false killer whales sound production rates around feeding times supports the hypothesis of the presence of a food anticipatory vocal activity. Although sound rates may not give detailed information regarding referential aspects of the animal communication it might still shed light about the arousal levels of the individuals during different social or environmental conditions. Further experiments should be performed to assess if variations of the time of feeding routines may affect the vocal activity of cetaceans in captivity as well as their welfare.展开更多
Modern leather industries are focused on producing high quality leather products for sustaining the market com-petitiveness. However, various leather defects are introduced during various stages of manufacturing proce...Modern leather industries are focused on producing high quality leather products for sustaining the market com-petitiveness. However, various leather defects are introduced during various stages of manufacturing process such as material handling, tanning and dyeing. Manual inspection of leather surfaces is subjective and inconsistent in nature;hence machine vision systems have been widely adopted for the automated inspection of leather defects. It is neces-sary develop suitable image processing algorithms for localize leather defects such as folding marks, growth marks, grain off, loose grain, and pinhole due to the ambiguous texture pattern and tiny nature in the localized regions of the leather. This paper presents deep learning neural network-based approach for automatic localization and classifica-tion of leather defects using a machine vision system. In this work, popular convolutional neural networks are trained using leather images of different leather defects and a class activation mapping technique is followed to locate the region of interest for the class of leather defect. Convolution neural networks such as Google net, Squeeze-net, RestNet are found to provide better accuracy of classification as compared with the state-of-the-art neural network architectures and the results are presented.展开更多
Introduction In China, it is not uncommon for students to be treated as passive recipients in class. They are trained in this way from primary school. So by the time they enter college, not only are they accustomed to...Introduction In China, it is not uncommon for students to be treated as passive recipients in class. They are trained in this way from primary school. So by the time they enter college, not only are they accustomed to the role of submissive student following the lead of a dominant teacher, but they also quite welcome it, for they don’t have to take any initiative in class, they just wait to be filled with knowledge. Students’ hesitancy to participate actively in class comes not just from students themselves but also from some teachers, who stick to the force-feeding method because it is an easy way for them to conduct a class. So I started to try and change this situation. I designed a teaching plan in which I used different techniques to provide the students with lots of opportunities to be active participants in class. Some of the techniques used are described below.展开更多
Introduction In this article, I’d like to describe a writing activity I use to improve my students’ writing ability. The activity is a type of journal-keeping for college-English students. I ask the students to writ...Introduction In this article, I’d like to describe a writing activity I use to improve my students’ writing ability. The activity is a type of journal-keeping for college-English students. I ask the students to write something at regular intervals. It can be of any length. If they don’t have anything specific to write about, they can write summaries or discussions about texts from their English class. They then submit the assignment by a fixed deadline. The results have been satisfactory. Most students handed in some sort of work on time, covering a wide range of topics from personal matters (such as worries and ambitions), interests (such as hobbies, friends and hometowns) to something related to their English class (summaries, discussions or even transcriptions of model paragraphs). Stimulated by immediate feedback from the teacher, the activity has continued through the whole college-English learning period.展开更多
文摘Education in the new era advocates taking students as the main body and improving students’core literacy on this basis.Subjectivity has also become one of the keys to quality education.Primary school is not only the initial stage of life,but also the key period to develop students’subjectivity.At present,there are many problems in class activities,such as the weak concept of taking students as the main body,the lack of subject consciousness among students,the flawed construction system of class activities,the unreasonable evaluation system of class activities,and so on.By establishing the role-playing model under the background of“class activity month,”students can play different roles in class activities and participate in various links,such as theme selection,scheme design,organization,implementation,summary,and evaluation of class activities.Through this process,it does not only improve the quality of class activities,but also cultivate students’subject consciousness and ability in a certain subject,thus highlighting their subject status in class activities.
文摘In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.
文摘Interest is the precondition and motivation for people's accomplishment.However,due to the exam-oriented system,millions of parents and teachers neglect the interests of children,and our children nearly forget their interests or hobbies.Based on different interests of children,the thesis analyzes how to apply the goal-setting theory in the second classroom teaching activities of College English,using the example of Lushan College of Guangxi University of Technology.
基金supported by the National Natural Science Foundation of China(Nos.42374150,42374152)Natural Science Foundation of Shandong Province(ZR2020MD050).
文摘The shear wave(S-wave)velocity is a critical rock elastic parameter in shale reservoirs,especially for evaluating shale fracability.To effectively supplement S-wave velocity under the condition of no actual measurement data,this paper proposes a physically-data driven method for the S-wave velocity prediction in shale reservoirs based on the class activation mapping(CAM)technique combined with a physically constrained two-dimensional Convolutional Neural Network(2D-CNN).High-sensitivity log curves related to S-wave velocity are selected as the basis from the data sensitivity analysis.Then,we establish a petrophysical model of complex multi-mineral components based on the petrophysical properties of porous medium and the Biot-Gassmann equation.This model can help reduce the dispersion effect and constrain the 2D-CNN.In deep learning,the 2D-CNN model is optimized using the Adam,and the class activation maps(CAMs)are obtained by replacing the fully connected layer with the global average pooling(GAP)layer,resulting in explainable results.The model is then applied to wells A,B1,and B2 in the southern Songliao Basin,China and compared with the unconstrained model and the petrophysical model.The results show higher prediction accuracy and generalization ability,as evidenced by correlation coefficients and relative errors of 0.98 and 2.14%,0.97 and 2.35%,0.96 and 2.89%in the three test wells,respectively.Finally,we present the defined C-factor as a means of evaluating the extent of concern regarding CAMs in regression problems.When the results of the petrophysical model are added to the 2D feature maps,the C-factor values are significantly increased,indicating that the focus of 2D-CNN can be significantly enhanced by incorporating the petrophysical model,thereby imposing physical constraints on the 2D-CNN.In addition,we establish the SHAP model,and the results of the petrophysical model have the highest average SHAP values across the three test wells.This helps to assist in proving the importance of constraints.
基金funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.
基金supported by a Korea Agency for Infrastructure Technology Advancement(KAIA)grant funded by the Ministry of Land,Infrastructure,and Transport(Grant 22CTAP-C163951-02).
文摘Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however,the predicted results have uncertainty in providing accurate informa-tion to users because of the“black box”problem in the deep learning model.Therefore,this study proposes a visual explanation method to overcome the uncertainty limitation of CNN-based defect identification.The visual repre-sentative gradient-weights class activation mapping(Grad-CAM)method is adopted to provide visually explainable information.A visualizing evaluation index is proposed to quantitatively analyze visual representations;this index reflects a rough estimate of the concordance rate between the visualized heat map and intended defects.In addition,an ablation study,adopting three-branch combinations with the VGG16,is implemented to identify perfor-mance variations by visualizing predicted results.Experiments reveal that the proposed model,combined with hybrid pooling,batch normalization,and multi-attention modules,achieves the best performance with an accuracy of 97.77%,corresponding to an improvement of 2.49%compared with the baseline model.Consequently,this study demonstrates that reliable results from an automatic defect classification model can be provided to an inspector through the visual representation of the predicted results using CNN models.
基金The research is funded by the Researchers Supporting Project at King Saud University,(Project#RSP-2021/305).
文摘COVID-19 is a growing problem worldwide with a high mortality rate.As a result,the World Health Organization(WHO)declared it a pandemic.In order to limit the spread of the disease,a fast and accurate diagnosis is required.A reverse transcript polymerase chain reaction(RT-PCR)test is often used to detect the disease.However,since this test is time-consuming,a chest computed tomography(CT)or plain chest X-ray(CXR)is sometimes indicated.The value of automated diagnosis is that it saves time and money by minimizing human effort.Three significant contributions are made by our research.Its initial purpose is to use the essential finetuning methodology to test the action and efficiency of a variety of vision models,ranging from Inception to Neural Architecture Search(NAS)networks.Second,by plotting class activationmaps(CAMs)for individual networks and assessing classification efficiency with AUC-ROC curves,the behavior of these models is visually analyzed.Finally,stacked ensembles techniques were used to provide greater generalization by combining finetuned models with six ensemble neural networks.Using stacked ensembles,the generalization of the models improved.Furthermore,the ensemble model created by combining all of the finetuned networks obtained a state-of-the-art COVID-19 accuracy detection score of 99.17%.The precision and recall rates were 99.99%and 89.79%,respectively,highlighting the robustness of stacked ensembles.The proposed ensemble approach performed well in the classification of the COVID-19 lesions on CXR according to the experimental results.
文摘The multi-media teaching method refers to using computer as a teaching assistant in the teaching Chinese as the second language （TCSL） class. The purpose of employing multi-media technology is to encourage students＇ class participation, giving them explicit and specific impression of abstract contents and cultivating their intuitive grasp of linguistic points. Based on the current study of usage of multi-media technology in class teaching, this paper attempts to investigate mainly on its positive influence of multi-media technology in teaching.
文摘The statistical study of F2 layer critical frequency at Dakar station from 1971 to 1996 is carried out. This paper shows foF2 statistical diurnal for all geomagnetic activities and all seasons and that during solar maximum and minimum phases. It emerges that foF2 diurnal variation graphs at Dakar station exhibits the different types of foF2 profiles in African EIA regions. The type of profile depends on solar activity, season and solar phase. During solar minimum and under quiet time condition, data show?the signature of a strength electrojet that is coupled with intense counter electrojet in the afternoon. Under disturbed conditions,?mean intense electrojet is observed in winter?during fluctuating and recurrent activities. Intense counter electrojet is seen under fluctuating and shock activities in all seasons coupled with strength electrojet in autumn. In summer?and spring under all geomagnetic activity condition, there is intense counter electrojet. During solar maximum, in summer and spring there is no electrojet under geomagnetic activity conditions.?Winter shows a mean intense electrojet. Winter and autumn are marked by the signature of the reversal electric field.
基金supported by the National Key Research & Development Plan of China (No. 2017YFB1002804)National Natural Science Foundation of China (Nos. 61425017, 61773379, 61332017, 61603390 and 61771472)the Major Program for the 325 National Social Science Fund of China (No. 13&ZD189)
文摘Facial emotion recognition is an essential and important aspect of the field of human-machine interaction.Past research on facial emotion recognition focuses on the laboratory environment.However,it faces many challenges in real-world conditions,i.e.,illumination changes,large pose variations and partial or full occlusions.Those challenges lead to different face areas with different degrees of sharpness and completeness.Inspired by this fact,we focus on the authenticity of predictions generated by different<emotion,region>pairs.For example,if only the mouth areas are available and the emotion classifier predicts happiness,then there is a question of how to judge the authenticity of predictions.This problem can be converted into the contribution of different face areas to different emotions.In this paper,we divide the whole face into six areas:nose areas,mouth areas,eyes areas,nose to mouth areas,nose to eyes areas and mouth to eyes areas.To obtain more convincing results,our experiments are conducted on three different databases:facial expression recognition+(FER+),real-world affective faces database(RAF-DB)and expression in-the-wild(ExpW)dataset.Through analysis of the classification accuracy,the confusion matrix and the class activation map(CAM),we can establish convincing results.To sum up,the contributions of this paper lie in two areas:1)We visualize concerned areas of human faces in emotion recognition;2)We analyze the contribution of different face areas to different emotions in real-world conditions through experimental analysis.Our findings can be combined with findings in psychology to promote the understanding of emotional expressions.
文摘In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to obtain.Therefore,it makes sense to learn more information(knowledge)from a small number of hard-to-get pixel-level annotated images to apply to different tasks to maximize their usefulness and save time and training costs.In this paper,using Pixel-Level Labeled Images forMulti-Task Learning(PLDMLT),we focus on grading the severity of fundus images for Diabetic Retinopathy(DR).This is because,for the segmentation task,there is a finely labeled mask,while the severity grading task is without classification labels.To this end,we propose a two-stage multi-label learning weakly supervised algorithm,which generates initial classification pseudo labels in the first stage and visualizes heat maps at all levels of severity using Grad-Cam to further provide medical interpretability for the classification task.A multitask model framework with U-net as the baseline is proposed in the second stage.A label update network is designed to alleviate the gradient balance between the classification and segmentation tasks.Extensive experimental results show that our PLDMLTmethod significantly outperforms other stateof-the-art methods in DR segmentation on two public datasets,achieving up to 98.897%segmentation accuracy.In addition,our method achieves comparable competitiveness with single-task fully supervised learning in the DR severity grading task.
文摘Segmenting dark-field images of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray light interference. Fully supervised semantic segmentation algorithms have achieved state-of-the-art performance but rely on a large number of pixel-level labels, which are time-consuming and labor-consuming to produce. LayerCAM, an advanced weakly supervised semantic segmentation algorithm, can generate pixel-accurate results using only image-level labels, but its scattered and partially underactivated class activation regions degrade segmentation performance. In this paper, we propose a weakly supervised semantic segmentation method, continuous gradient class activation mapping(CAM) and its nonlinear multiscale fusion(continuous gradient fusion CAM). The method redesigns backpropagating gradients and nonlinearly activates multiscale fused heatmaps to generate more fine-grained class activation maps with an appropriate activation degree for different damage site sizes. Experiments on our dataset show that the proposed method can achieve segmentation performance comparable to that of fully supervised algorithms.
基金This research is partially supported by the Programme for Professor of Special Appointment(Eastern Scholar)at Shanghai Institutions of Higher Learning,and also partially supported by JSPS KAKENHI Grant No.15K00159.
文摘Scene recognition is a fundamental task in computer vision,which generally includes three vital stages,namely feature extraction,feature transformation and classification.Early research mainly focuses on feature extraction,but with the rise of Convolutional Neural Networks(CNNs),more and more feature transformation methods are proposed based on CNN features.In this work,a novel feature transformation algorithm called Graph Encoded Local Discriminative Region Representation(GEDRR)is proposed to find discriminative local representations for scene images and explore the relationship between the discriminative regions.In addition,we propose a method using the multi-head attention module to enhance and fuse convolutional feature maps.Combining the two methods and the global representation,a scene recognition framework called Global and Graph Encoded Local Discriminative Region Representation(G2ELDR2)is proposed.The experimental results on three scene datasets demonstrate the effectiveness of our model,which outperforms many state-of-the-arts.
基金This research has been funded by the Research General Direction at Universidad Santiago de Cali under call No.01-2021.
文摘The most salient argument that needs to be addressed universally is Early Breast Cancer Detection(EBCD),which helps people live longer lives.The Computer-Aided Detection(CADs)/Computer-Aided Diagnosis(CADx)sys-tem is indeed a software automation tool developed to assist the health profes-sions in Breast Cancer Detection and Diagnosis(BCDD)and minimise mortality by the use of medical histopathological image classification in much less time.This paper purposes of examining the accuracy of the Convolutional Neural Network(CNN),which can be used to perceive breast malignancies for initial breast cancer detection to determine which strategy is efficient for the early iden-tification of breast cell malignancies formation of masses and Breast microcalci-fications on the mammogram.When we have insufficient data for a new domain that is desired to be handled by a pre-trained Convolutional Neural Network of Residual Network(ResNet50)for Breast Cancer Detection and Diagnosis,to obtain the Discriminative Localization,Convolutional Neural Network with Class Activation Map(CAM)has also been used to perform breast microcalcifications detection tofind a specific class in the Histopathological image.The test results indicate that this method performed almost 225.15%better at determining the exact location of disease(Discriminative Localization)through breast microcalci-fications images.ResNet50 seems to have the highest level of accuracy for images of Benign Tumour(BT)/Malignant Tumour(MT)cases at 97.11%.ResNet50’s average accuracy for pre-trained Convolutional Neural Network is 94.17%.
文摘This paper proposes an accurate,efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network(CNN).The state-of-the-art robust CNN model(EfficientNet)is applied to tunnel wall image recognition.Gaussian filtering,data augmentation and other data pre-processing techniques are used to improve the data quality and quantity.Combined with transfer learning,the generality,accuracy and efficiency of the deep learning(DL)model are further improved,and finally we achieve 89.96%accuracy.Compared with other state-of-the-art CNN architectures,such as ResNet and Inception-ResNet-V2(IRV2),the presented deep transfer learning model is more stable,accurate and efficient.To reveal the rock classification mechanism of the proposed model,Gradient-weight Class Activation Map(Grad-CAM)visualizations are integrated into the model to enable its explainability and accountability.The developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou,China,with great results.
文摘In the teaching process of kindergarten teachers, curriculum activities such as creation and compilation of children's dance not only play a good role in promoting the optimization of students' knowledge structure, but also can improve students' dance literacy, and improve students' innovative ability and comprehensive practical ability, which is also a prerequisite for their future growth as an excellent kindergarten teacher. This paper aims at the problems in the process of setting up dance creation course for children, analyzes the necessity of setting up this activity course, and finally puts forward several feasible measures to effectively carry out the activity course according to the current situation.
基金Supported by grants from the Institute of Hydrobiology,Chinese Academy of Sciences
文摘This study examines whether a group of captive false killer whales(P seudorca crassidens) showed variations in the vocal rate around feeding times. The high level of motivation to express appetitive behaviors in captive animals may lead them to respond with changes of the behavioral activities during the time prior to food deliveries which are referred to as food anticipatory activity. False killer whales at Qingdao Polar Ocean World(Qingdao, China) showed signifi cant variations of the rates of both the total sounds and sound classes(whistles, clicks, and burst pulses) around feedings. Precisely, from the Transition interval that recorded the lowest vocalization rate(3.40 s/m/d), the whales increased their acoustic emissions upon trainers' arrival(13.08 s/m/d). The high rate was maintained or intensifi ed throughout the food delivery(25.12 s/m/d), and then reduced immediately after the animals were fed(9.91 s/m/d). These changes in the false killer whales sound production rates around feeding times supports the hypothesis of the presence of a food anticipatory vocal activity. Although sound rates may not give detailed information regarding referential aspects of the animal communication it might still shed light about the arousal levels of the individuals during different social or environmental conditions. Further experiments should be performed to assess if variations of the time of feeding routines may affect the vocal activity of cetaceans in captivity as well as their welfare.
文摘Modern leather industries are focused on producing high quality leather products for sustaining the market com-petitiveness. However, various leather defects are introduced during various stages of manufacturing process such as material handling, tanning and dyeing. Manual inspection of leather surfaces is subjective and inconsistent in nature;hence machine vision systems have been widely adopted for the automated inspection of leather defects. It is neces-sary develop suitable image processing algorithms for localize leather defects such as folding marks, growth marks, grain off, loose grain, and pinhole due to the ambiguous texture pattern and tiny nature in the localized regions of the leather. This paper presents deep learning neural network-based approach for automatic localization and classifica-tion of leather defects using a machine vision system. In this work, popular convolutional neural networks are trained using leather images of different leather defects and a class activation mapping technique is followed to locate the region of interest for the class of leather defect. Convolution neural networks such as Google net, Squeeze-net, RestNet are found to provide better accuracy of classification as compared with the state-of-the-art neural network architectures and the results are presented.
文摘Introduction In China, it is not uncommon for students to be treated as passive recipients in class. They are trained in this way from primary school. So by the time they enter college, not only are they accustomed to the role of submissive student following the lead of a dominant teacher, but they also quite welcome it, for they don’t have to take any initiative in class, they just wait to be filled with knowledge. Students’ hesitancy to participate actively in class comes not just from students themselves but also from some teachers, who stick to the force-feeding method because it is an easy way for them to conduct a class. So I started to try and change this situation. I designed a teaching plan in which I used different techniques to provide the students with lots of opportunities to be active participants in class. Some of the techniques used are described below.
文摘Introduction In this article, I’d like to describe a writing activity I use to improve my students’ writing ability. The activity is a type of journal-keeping for college-English students. I ask the students to write something at regular intervals. It can be of any length. If they don’t have anything specific to write about, they can write summaries or discussions about texts from their English class. They then submit the assignment by a fixed deadline. The results have been satisfactory. Most students handed in some sort of work on time, covering a wide range of topics from personal matters (such as worries and ambitions), interests (such as hobbies, friends and hometowns) to something related to their English class (summaries, discussions or even transcriptions of model paragraphs). Stimulated by immediate feedback from the teacher, the activity has continued through the whole college-English learning period.
