Deep learning has achieved excellent results in various tasks in the field of computer vision,especially in fine-grained visual categorization.It aims to distinguish the subordinate categories of the label-level categ...Deep learning has achieved excellent results in various tasks in the field of computer vision,especially in fine-grained visual categorization.It aims to distinguish the subordinate categories of the label-level categories.Due to high intra-class variances and high inter-class similarity,the fine-grained visual categorization is extremely challenging.This paper first briefly introduces and analyzes the related public datasets.After that,some of the latest methods are reviewed.Based on the feature types,the feature processing methods,and the overall structure used in the model,we divide them into three types of methods:methods based on general convolutional neural network(CNN)and strong supervision of parts,methods based on single feature processing,and meth-ods based on multiple feature processing.Most methods of the first type have a relatively simple structure,which is the result of the initial research.The methods of the other two types include models that have special structures and training processes,which are helpful to obtain discriminative features.We conduct a specific analysis on several methods with high accuracy on pub-lic datasets.In addition,we support that the focus of the future research is to solve the demand of existing methods for the large amount of the data and the computing power.In terms of tech-nology,the extraction of the subtle feature information with the burgeoning vision transformer(ViT)network is also an important research direction.展开更多
The quality of oranges is grounded on their appearance and diameter.Appearance refers to the skin’s smoothness and surface cleanliness;diameter refers to the transverse diameter size.They are visual attributes that v...The quality of oranges is grounded on their appearance and diameter.Appearance refers to the skin’s smoothness and surface cleanliness;diameter refers to the transverse diameter size.They are visual attributes that visual perception technologies can automatically identify.Nonetheless,the current orange quality assessment needs to address two issues:1)There are no image datasets for orange quality grading;2)It is challenging to effectively learn the fine-grained and distinct visual semantics of oranges from diverse angles.This study collected 12522 images from 2087 oranges for multi-grained grading tasks.In addition,it presented a visual learning graph convolution approach for multi-grained orange quality grading,including a backbone network and a graph convolutional network(GCN).The backbone network’s object detection,data augmentation,and feature extraction can remove extraneous visual information.GCN was utilized to learn the topological semantics of orange feature maps.Finally,evaluation results proved that the recognition accuracy of diameter size,appearance,and fine-grained orange quality were 99.50,97.27,and 97.99%,respectively,indicating that the proposed approach is superior to others.展开更多
Localizing discriminative object parts(e.g.,bird head)is crucial for fine-grained classification tasks,especially for the more challenging fine-grained few-shot scenario.Previous work always relies on the learned obje...Localizing discriminative object parts(e.g.,bird head)is crucial for fine-grained classification tasks,especially for the more challenging fine-grained few-shot scenario.Previous work always relies on the learned object parts in a unified manner,where they attend the same object parts(even with common attention weights)for different few-shot episodic tasks.In this paper,we propose that it should adaptively capture the task-specific object parts that require attention for each few-shot task,since the parts that can distinguish different tasks are naturally different.Specifically for a few-shot task,after obtaining part-level deep features,we learn a task-specific part-based dictionary for both aligning and reweighting part features in an episode.Then,part-level categorical prototypes are generated based on the part features of support data,which are later employed by calculating distances to classify query data for evaluation.To retain the discriminative ability of the part-level representations(i.e.,part features and part prototypes),we design an optimal transport solution that also utilizes query data in a transductive way to optimize the aforementioned distance calculation for the final predictions.Extensive experiments on five fine-grained benchmarks show the superiority of our method,especially for the 1-shot setting,gaining 0.12%,8.56%and 5.87%improvements over state-of-the-art methods on CUB,Stanford Dogs,and Stanford Cars,respectively.展开更多
Visual categorization can be derived from interaction between inputting features set (IFS) from outside stimuli and anticipating features set (AFS) from concept, and such interaction can take two forms: match extracti...Visual categorization can be derived from interaction between inputting features set (IFS) from outside stimuli and anticipating features set (AFS) from concept, and such interaction can take two forms: match extraction and conflict control. Us- ing ERP recording, we investigated the temporal course of visual categorization. The results indicated that the larger the AFS, the higher the amplitude of the N1 was generated, which demonstrated the effect of the AFS on the attention. When the size of the AFS was larger than or equal to 2, prominent N2 compo- nent was elicited, which demonstrated the effect of conflict when the feature of IFS mismatched with the feature of the AFS. The judgment of category was manifested on the LPC component, and this com- ponent was also sensitive to conflict control. Based on the results, we proposed that the temporal course of visual categorization was as follows: selective at- tention, feature perception, feature match/extraction and judgment of category/conflict control. Among those processes, the judgment of category is the core processing; however the former three sub-processes form the base of categorization. The results are in support of the idea that LPC is responsible for high- level categorization process.展开更多
针对传统的视觉词袋(bag of visual words,BoVW)模型忽略了视觉单词的空间位置信息的问题,文章提出一种基于视觉单词共生矩阵的图像分类方法。首先对整幅图像进行空间金字塔分解,得到一系列图像块;然后针对每一图像块中的SIFT点,在其空...针对传统的视觉词袋(bag of visual words,BoVW)模型忽略了视觉单词的空间位置信息的问题,文章提出一种基于视觉单词共生矩阵的图像分类方法。首先对整幅图像进行空间金字塔分解,得到一系列图像块;然后针对每一图像块中的SIFT点,在其空间邻域范围内构建视觉单词共生矩阵(visual words co-occurrence matrix,VWCM)单元,并得到该图像块对应的视觉单词共生矩阵;最后设计出一种新的空间金字塔共生矩阵核(spatial pyramid co-occurrence matrix kernel,SPCMK),并将其用于图像分类。该方法能够有效地刻画视觉单词的绝对和相对位置信息,极大地增强了图像表达的完整度与准确度。实验结果表明,文章方法确实能够大幅度提高图像分类的准确率。展开更多
基金supported by the National Natural Science Foundation of China(61571453,61806218).
文摘Deep learning has achieved excellent results in various tasks in the field of computer vision,especially in fine-grained visual categorization.It aims to distinguish the subordinate categories of the label-level categories.Due to high intra-class variances and high inter-class similarity,the fine-grained visual categorization is extremely challenging.This paper first briefly introduces and analyzes the related public datasets.After that,some of the latest methods are reviewed.Based on the feature types,the feature processing methods,and the overall structure used in the model,we divide them into three types of methods:methods based on general convolutional neural network(CNN)and strong supervision of parts,methods based on single feature processing,and meth-ods based on multiple feature processing.Most methods of the first type have a relatively simple structure,which is the result of the initial research.The methods of the other two types include models that have special structures and training processes,which are helpful to obtain discriminative features.We conduct a specific analysis on several methods with high accuracy on pub-lic datasets.In addition,we support that the focus of the future research is to solve the demand of existing methods for the large amount of the data and the computing power.In terms of tech-nology,the extraction of the subtle feature information with the burgeoning vision transformer(ViT)network is also an important research direction.
基金supported by the National Natural Science Foundation of China(31901240,31971792)the Science and Technology Innovation Program of the Chinese Academy of Agricultural Sciences(CAAS-ASTIP-2016-AⅡ)the Central Public-interest Scientific Institution Basal Research Funds,China(Y2022QC17,CAAS-ZDRW202107).
文摘The quality of oranges is grounded on their appearance and diameter.Appearance refers to the skin’s smoothness and surface cleanliness;diameter refers to the transverse diameter size.They are visual attributes that visual perception technologies can automatically identify.Nonetheless,the current orange quality assessment needs to address two issues:1)There are no image datasets for orange quality grading;2)It is challenging to effectively learn the fine-grained and distinct visual semantics of oranges from diverse angles.This study collected 12522 images from 2087 oranges for multi-grained grading tasks.In addition,it presented a visual learning graph convolution approach for multi-grained orange quality grading,including a backbone network and a graph convolutional network(GCN).The backbone network’s object detection,data augmentation,and feature extraction can remove extraneous visual information.GCN was utilized to learn the topological semantics of orange feature maps.Finally,evaluation results proved that the recognition accuracy of diameter size,appearance,and fine-grained orange quality were 99.50,97.27,and 97.99%,respectively,indicating that the proposed approach is superior to others.
基金supported by National Natural Science Foundation of China(No.62272231)Natural Science Foundation of Jiangsu Province of China(No.BK 20210340)+2 种基金National Key R&D Program of China(No.2021YFA1001100)the Fundamental Research Funds for the Central Universities,China(No.NJ2022028)CAAI-Huawei MindSpore Open Fund,China.
文摘Localizing discriminative object parts(e.g.,bird head)is crucial for fine-grained classification tasks,especially for the more challenging fine-grained few-shot scenario.Previous work always relies on the learned object parts in a unified manner,where they attend the same object parts(even with common attention weights)for different few-shot episodic tasks.In this paper,we propose that it should adaptively capture the task-specific object parts that require attention for each few-shot task,since the parts that can distinguish different tasks are naturally different.Specifically for a few-shot task,after obtaining part-level deep features,we learn a task-specific part-based dictionary for both aligning and reweighting part features in an episode.Then,part-level categorical prototypes are generated based on the part features of support data,which are later employed by calculating distances to classify query data for evaluation.To retain the discriminative ability of the part-level representations(i.e.,part features and part prototypes),we design an optimal transport solution that also utilizes query data in a transductive way to optimize the aforementioned distance calculation for the final predictions.Extensive experiments on five fine-grained benchmarks show the superiority of our method,especially for the 1-shot setting,gaining 0.12%,8.56%and 5.87%improvements over state-of-the-art methods on CUB,Stanford Dogs,and Stanford Cars,respectively.
基金supported by National Natural Science Foundation of China(Grant Nos.30370488&30325026)National Key Subject of Basic Psychology Southwest University,China(Grant No.XGZ04006).
文摘Visual categorization can be derived from interaction between inputting features set (IFS) from outside stimuli and anticipating features set (AFS) from concept, and such interaction can take two forms: match extraction and conflict control. Us- ing ERP recording, we investigated the temporal course of visual categorization. The results indicated that the larger the AFS, the higher the amplitude of the N1 was generated, which demonstrated the effect of the AFS on the attention. When the size of the AFS was larger than or equal to 2, prominent N2 compo- nent was elicited, which demonstrated the effect of conflict when the feature of IFS mismatched with the feature of the AFS. The judgment of category was manifested on the LPC component, and this com- ponent was also sensitive to conflict control. Based on the results, we proposed that the temporal course of visual categorization was as follows: selective at- tention, feature perception, feature match/extraction and judgment of category/conflict control. Among those processes, the judgment of category is the core processing; however the former three sub-processes form the base of categorization. The results are in support of the idea that LPC is responsible for high- level categorization process.
