Negative Prototypes Guided Contrastive Learning for WSOD
Weakly Supervised Object Detection (WSOD) with only image-level annotation has recently attracted wide attention. Many existing methods ignore the inter-image relationship of instances which share similar characteristics while can certainly be determined not to belong to the same category. Therefore, in order to make full use of the weak label, we propose the Negative Prototypes Guided Contrastive learning (NPGC) architecture. Firstly, we define Negative Prototype as the proposal with the highest confidence score misclassified for the category that does not appear in the label. Unlike other methods that only utilize category positive feature, we construct an online updated global feature bank to store both positive prototypes and negative prototypes. Meanwhile, we propose a pseudo label sampling module to mine reliable instances and discard the easily misclassified instances based on the feature similarity with corresponding prototypes in global feature bank. Finally, we follow the contrastive learning paradigm to optimize the proposal's feature representation by attracting same class samples closer and pushing different class samples away in the embedding space. Extensive experiments have been conducted on VOC07, VOC12 datasets, which shows that our proposed method achieves the state-of-the-art performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive Learningobject-detectionObject DetectionPseudo LabelWeakly Supervised Object DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information
Weakly supervised object detection (WSOD) is a challenging task, in which image-level labels (e.g., categories of the instances in the whole image) are used to train an object detector. Many existing methods follow the s…
Contrastive LearningMultiple Instance Learningobject-detectionObject Detection+1Contrastive Learning with Prompt-derived Virtual Semantic Prototypes for Unsupervised Sentence Embedding
Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In…
ClusteringContrastive LearningData AugmentationSemantic Textual Similarity+4Towards Precise Weakly Supervised Object Detection via Interactive Contrastive Learning of Context Information
Weakly supervised object detection (WSOD) aims at learning precise object detectors with only image-level tags. In spite of intensive research on deep learning (DL) approaches over the past few years, there is still a si…
Contrastive LearningObjectobject-detectionObject Detection+2Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) has attracted more and more attention since it only uses image-level labels and can save huge annotation costs. Most of the WSOD methods use Multiple Instance Learning (MIL) as t…
Multiple Instance Learningobject-detectionObject DetectionWeakly Supervised Object DetectionDual-Thresholded Heatmap-Guided Proposal Clustering and Negative Certainty Supervision with Enhanced Base Network for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) has attracted significant attention in recent years, as it does not require box-level annotations. State-of-the-art methods generally adopt a multi-module network, which employs …
Weakly Supervised Object Detection