Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection
Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy. Hence, weakly supervised tasks, including weakly supervised object localization~(WSOL) and detection~(WSOD), have recently received attention in the computer vision community. In this paper, we motivate and propose the weakly supervised foreground learning (WSFL) task by showing that both WSOL and WSOD can be greatly improved if groundtruth foreground masks are available. More importantly, we propose a complete WSFL pipeline with low computational cost, which generates pseudo boxes, learns foreground masks, and does not need any localization annotations. With the help of foreground masks predicted by our WSFL model, we achieve 72.97% correct localization accuracy on CUB for WSOL, and 55.7% mean average precision on VOC07 for WSOD, thereby establish new state-of-the-art for both tasks. Our WSFL model also shows excellent transfer ability.
Code (0)
등록된 구현이 없습니다.
Tasks
Object LocalizationWeakly-Supervised Object LocalizationSimilar Papers 제목 키워드 기반
Cross-Attentional Audio-Visual Fusion for Weakly-Supervised Action Localization
Temporally localizing actions in videos is one of the key components for video understanding. Learning from weakly-labelled data is seen a potential solution towards avoiding expensive frame-level annotations. Different …
Action LocalizationVideo UnderstandingWeakly Supervised Action LocalizationIncorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fin…
Object RecognitionSegmentationSemantic SegmentationTAG+2Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
Weakly supervised object localization and semantic segmentation aim to localize objects using only image-level labels. Recently, a new paradigm has emerged by generating a foreground prediction map (FPM) to achieve pixel…
ObjectObject LocalizationSemantic SegmentationWeakly-Supervised Object Localization+2Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving
Understanding motion in dynamic environments is critical for autonomous driving, thereby motivating research on class-agnostic motion prediction. In this work, we investigate weakly and self-supervised class-agnostic mot…
Self-Supervised LearningAutonomous DrivingScene ParsingPoint CloudsImproving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label
Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly…
ObjectObject LocalizationPseudo LabelWeakly-supervised Learning+1