Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
Weakly-supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos using only video-level supervision. Latest WSTAL methods introduce pseudo label learning framework to bridge the gap between classification-based training and inferencing targets at localization, and achieve cutting-edge results. In these frameworks, a classification-based model is used to generate pseudo labels for a regression-based student model to learn from. However, the quality of pseudo labels in the framework, which is a key factor to the final result, is not carefully studied. In this paper, we propose a set of simple yet efficient pseudo label quality enhancement mechanisms to build our FuSTAL framework. FuSTAL enhances pseudo label quality at three stages: cross-video contrastive learning at proposal Generation-Stage, prior-based filtering at proposal Selection-Stage and EMA-based distillation at Training-Stage. These designs enhance pseudo label quality at different stages in the framework, and help produce more informative, less false and smoother action proposals. With the help of these comprehensive designs at all stages, FuSTAL achieves an average mAP of 50.8% on THUMOS'14, outperforming the previous best method by 1.2%, and becomes the first method to reach the milestone of 50%.
Code (1)
Tasks
Action LocalizationContrastive LearningPseudo LabelTemporal Action LocalizationWeakly-supervised Temporal Action LocalizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cross-Domain Underwater Image Enhancement Guided by No-Reference Image Quality Assessment: A Transfer Learning Approach
Single underwater image enhancement (UIE) is a challenging ill-posed problem, but its development is hindered by two major issues: (1) The labels in underwater reference datasets are pseudo labels, relying on these pseud…
Image EnhancementImage Quality AssessmentNo-Reference Image Quality AssessmentNR-IQA+2Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning
By leveraging data from a fully labeled source domain, unsupervised domain adaptation (UDA) improves classification performance on an unlabeled target domain through explicit discrepancy minimization of data distribution…
Domain AdaptationPseudo LabelUnsupervised Domain AdaptationExploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection
Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseu…
Anomaly DetectionDiversityPseudo LabelVideo Anomaly Detection+1You Only Click Once: Single Point Weakly Supervised 3D Instance Segmentation for Autonomous Driving
Outdoor LiDAR point cloud 3D instance segmentation is a crucial task in autonomous driving. However, it requires laborious human efforts to annotate the point cloud for training a segmentation model. To address this chal…
3D Instance SegmentationAutonomous DrivingInstance SegmentationPseudo Label+1S4OD: Semi-Supervised learning for Single-Stage Object Detection
Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance b…
Objectobject-detectionObject Detectionregression+1