Rethinking Weak-to-Strong Augmentation in Source-Free Domain Adaptive Object Detection
Source-Free domain adaptive Object Detection (SFOD) aims to transfer a detector (pre-trained on source domain) to new unlabelled target domains. Current SFOD methods typically follow the Mean Teacher framework, where weak-to-strong augmentation provides diverse and sharp contrast for self-supervised learning. However, this augmentation strategy suffers from an inherent problem called crucial semantics loss: Due to random, strong disturbance, strong augmentation is prone to losing typical visual components, hindering cross-domain feature extraction. To address this thus-far ignored limitation, this paper introduces a novel Weak-to-Strong Contrastive Learning (WSCoL) approach. The core idea is to distill semantics lossless knowledge in the weak features (from the weak/teacher branch) to guide the representation learning upon the strong features (from the strong/student branch). To achieve this, we project the original features into a shared space using a mapping network, thereby reducing the bias between the weak and strong features. Meanwhile, a weak features-guided contrastive learning is performed in a weak-to-strong manner alternatively. Specifically, we first conduct an adaptation-aware prototype-guided clustering on the weak features to generate pseudo labels for corresponding strong features matched through proposals. Sequentially, we identify positive-negative samples based on the pseudo labels and perform cross-category contrastive learning on the strong features where an uncertainty estimator encourages adaptive background contrast. Extensive experiments demonstrate that WSCoL yields new state-of-the-art performance, offering a built-in mechanism mitigating crucial semantics loss for traditional Mean Teacher framework. The code and data will be released soon.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive Learningobject-detectionObject DetectionRepresentation LearningSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning
Recent works have shown that self-supervised learning can achieve remarkable robustness when integrated with adversarial training (AT). However, the robustness gap between supervised AT (sup-AT) and self-supervised AT (s…
Contrastive LearningData AugmentationSelf-Supervised LearningSimplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights
This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain…
Domain Adaptationobject-detectionObject DetectionPseudo Label+2Strongly Augmented Contrastive Clustering
Deep clustering has attracted increasing attention in recent years due to its capability of joint representation learning and clustering via deep neural networks. In its latest developments, the contrastive learning has …
ClusteringContrastive LearningDeep ClusteringRepresentation LearningRethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking
Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However, as Large Language Models evolve with i…
Does Data Augmentation Improve Generalization in NLP?
Neural models often exploit superficial features to achieve good performance, rather than deriving more general features. Overcoming this tendency is a central challenge in areas such as representation learning and ML fa…
Data AugmentationFairnessRepresentation Learning