Generalizable pedestrian attribute recognition(PAR)aims to learn a robust PAR model that can be directly adapted to unknown distributions under varying illumination,different viewpoints and occlusions,which is an esse...Generalizable pedestrian attribute recognition(PAR)aims to learn a robust PAR model that can be directly adapted to unknown distributions under varying illumination,different viewpoints and occlusions,which is an essential problem for real-world applications,such as video surveillance and fashion search.In practice,when a trained PAR model is deployed to real-world scenarios,the unseen target samples are fed into the model continuously in an online manner.Therefore,this paper proposes an efficient and flexible method,named AdaGPAR,for generalizable PAR(GPAR)via test-time adaptation(TTA),where we adapt the trained model through exploiting the unlabeled target samples online during the test phase.As far as we know,it is the first work that solves the GPAR from the perspective of TTA.In particular,the proposed AdaGPAR memorizes the reliable target sample pairs(features and pseudo-labels)as prototypes gradually in the test phase.Then,it makes predictions with a non-parametric classifier by calculating the similarity between a target instance and the prototypes.However,since PAR is a task of multi-label classification,only using the same holistic feature of one pedestrian image as the prototypes of multiple attributes is not optimal.Therefore,an attribute localization branch is introduced to extract the attribute-specific features,where two kinds of memory banks are further constructed to cache the global and attribute-specific features simultaneously.In summary,the AdaGPAR is training-free in the test phase and predicts multiple pedestrian attributes of the target samples in an online manner.This makes the AdaGPAR time efficient and generalizable for real-world applications.Extensive experiments have been performed on the UPAR benchmark to compare the proposed method with multiple baselines.The superior performance demonstrates the effectiveness of the proposed AdaGPAR that improves the generalizability of a PAR model via TTA.展开更多
As network and information systems become widely adopted across industries,cybersecurity concerns have grown more prominent.Among these concerns,insider threats are considered particularly covert and destructive.Insid...As network and information systems become widely adopted across industries,cybersecurity concerns have grown more prominent.Among these concerns,insider threats are considered particularly covert and destructive.Insider threats refer to malicious insiders exploiting privileged access to networks,systems,and data to intentionally compromise organizational security.Detecting these threats is challenging due to the complexity and variability of user behavior data,combined with the subtle and covert nature of insider actions.Traditional detection methods often fail to capture both long-term dependencies and short-term fluctuations in time-series data,which are crucial for identifying anomalous behaviors.To address these issues,this paper introduces the Test-Time Training(TTT)model for the first time in the field of insider threat detection,and proposes a detection method based on the TTT-ECA-ResNet model.First,the dataset is preprocessed.TTT is applied to extract long-term dependencies in features,effectively capturing dynamic sequence changes.The Residual Network,incorporating the Efficient Channel Attention mechanism,is used to extract local feature patterns,capturing relationships between different positions in time-series data.Finally,a Linear layer is employed for more precise detection of insider threats.The proposed approaches were evaluated using the CMU CERT Insider Threat Dataset,achieving an AUC of 98.75%and an F1-score of 96.81%.The experimental results demonstrate the effectiveness of the proposed methods,outperforming other state-of-the-art approaches.展开更多
Automatic and accurate medical image segmentation remains a fundamental task in computer-aided diagnosis and treatment planning.Recent advances in foundation models,such as the medical-focused Segment AnythingModel(Me...Automatic and accurate medical image segmentation remains a fundamental task in computer-aided diagnosis and treatment planning.Recent advances in foundation models,such as the medical-focused Segment AnythingModel(MedSAM),have demonstrated strong performance but face challenges inmanymedical applications due to anatomical complexity and a limited domain-specific prompt.Thiswork introduces amethodology that enhances segmentation robustness and precision by automatically generating multiple informative point prompts,rather than relying on single inputs.The proposed approach randomly samples sets of spatially distributed point prompts based on image features,enabling MedSAM to better capture fine-grained anatomical structures and boundaries.During inference,probability maps are aggregated to reduce local misclassifications without additional model training.Extensive experiments on various computed tomography(CT)and magnetic resonance imaging(MRI)datasets demonstrate improvements in Dice Similarity Coefficient(DSC)and Normalized Surface Dice(NSD)metrics compared to baseline SAM and Scribble Prompt models.A semi-automatic point sampling version based on the ground truth segmentations yielded enhanced results,achieving up to 92.1%DSC and 86.6%NSD,with significant gains in delineating complex organs such as the pancreas,colon,kidney,and brain tumours.The main novelty of our method consists of effectively combining the results of multiple point prompts into the medical segmentation pipeline so that single-point prompt methods are outperformed.Overall,the proposed model offers a straightforward yet effective approach to improve medical image segmentation performance while maintaining computational efficiency.展开更多
基金supported in part by the National Science and Technology Major project,China(No.2022ZD0117901)in part by the National Natural Science Foundation of China(Nos.62373355,62276256 and 62106260).
文摘Generalizable pedestrian attribute recognition(PAR)aims to learn a robust PAR model that can be directly adapted to unknown distributions under varying illumination,different viewpoints and occlusions,which is an essential problem for real-world applications,such as video surveillance and fashion search.In practice,when a trained PAR model is deployed to real-world scenarios,the unseen target samples are fed into the model continuously in an online manner.Therefore,this paper proposes an efficient and flexible method,named AdaGPAR,for generalizable PAR(GPAR)via test-time adaptation(TTA),where we adapt the trained model through exploiting the unlabeled target samples online during the test phase.As far as we know,it is the first work that solves the GPAR from the perspective of TTA.In particular,the proposed AdaGPAR memorizes the reliable target sample pairs(features and pseudo-labels)as prototypes gradually in the test phase.Then,it makes predictions with a non-parametric classifier by calculating the similarity between a target instance and the prototypes.However,since PAR is a task of multi-label classification,only using the same holistic feature of one pedestrian image as the prototypes of multiple attributes is not optimal.Therefore,an attribute localization branch is introduced to extract the attribute-specific features,where two kinds of memory banks are further constructed to cache the global and attribute-specific features simultaneously.In summary,the AdaGPAR is training-free in the test phase and predicts multiple pedestrian attributes of the target samples in an online manner.This makes the AdaGPAR time efficient and generalizable for real-world applications.Extensive experiments have been performed on the UPAR benchmark to compare the proposed method with multiple baselines.The superior performance demonstrates the effectiveness of the proposed AdaGPAR that improves the generalizability of a PAR model via TTA.
基金supported by the National Natural Science Foundation of China(62472118)the Central Guidance on Local Science and Technology Development Fund of GuangxiProvince(ZY23055008)+1 种基金the Guangxi Science and Technology Program(AB24010315)the Innovation Project of Guangxi Graduate Education,China(YCSW2024325).
文摘As network and information systems become widely adopted across industries,cybersecurity concerns have grown more prominent.Among these concerns,insider threats are considered particularly covert and destructive.Insider threats refer to malicious insiders exploiting privileged access to networks,systems,and data to intentionally compromise organizational security.Detecting these threats is challenging due to the complexity and variability of user behavior data,combined with the subtle and covert nature of insider actions.Traditional detection methods often fail to capture both long-term dependencies and short-term fluctuations in time-series data,which are crucial for identifying anomalous behaviors.To address these issues,this paper introduces the Test-Time Training(TTT)model for the first time in the field of insider threat detection,and proposes a detection method based on the TTT-ECA-ResNet model.First,the dataset is preprocessed.TTT is applied to extract long-term dependencies in features,effectively capturing dynamic sequence changes.The Residual Network,incorporating the Efficient Channel Attention mechanism,is used to extract local feature patterns,capturing relationships between different positions in time-series data.Finally,a Linear layer is employed for more precise detection of insider threats.The proposed approaches were evaluated using the CMU CERT Insider Threat Dataset,achieving an AUC of 98.75%and an F1-score of 96.81%.The experimental results demonstrate the effectiveness of the proposed methods,outperforming other state-of-the-art approaches.
基金supported by the Autonomous Government of Andalusia(Spain)under project UMA20-FEDERJA-108also by the Ministry of Science and Innovation of Spain,grant number PID2022-136764OA-I00+1 种基金It includes funds fromthe European Regional Development Fund(ERDF),It is also partially supported by the Fundación Unicaja(PUNI-003_2023)the Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND(ATECH-25-02).
文摘Automatic and accurate medical image segmentation remains a fundamental task in computer-aided diagnosis and treatment planning.Recent advances in foundation models,such as the medical-focused Segment AnythingModel(MedSAM),have demonstrated strong performance but face challenges inmanymedical applications due to anatomical complexity and a limited domain-specific prompt.Thiswork introduces amethodology that enhances segmentation robustness and precision by automatically generating multiple informative point prompts,rather than relying on single inputs.The proposed approach randomly samples sets of spatially distributed point prompts based on image features,enabling MedSAM to better capture fine-grained anatomical structures and boundaries.During inference,probability maps are aggregated to reduce local misclassifications without additional model training.Extensive experiments on various computed tomography(CT)and magnetic resonance imaging(MRI)datasets demonstrate improvements in Dice Similarity Coefficient(DSC)and Normalized Surface Dice(NSD)metrics compared to baseline SAM and Scribble Prompt models.A semi-automatic point sampling version based on the ground truth segmentations yielded enhanced results,achieving up to 92.1%DSC and 86.6%NSD,with significant gains in delineating complex organs such as the pancreas,colon,kidney,and brain tumours.The main novelty of our method consists of effectively combining the results of multiple point prompts into the medical segmentation pipeline so that single-point prompt methods are outperformed.Overall,the proposed model offers a straightforward yet effective approach to improve medical image segmentation performance while maintaining computational efficiency.
