Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Training
This study addresses the integration of diversity-based and uncertainty-based sampling strategies in active learning, particularly within the context of self-supervised pre-trained models. We introduce a straightforward heuristic called TCM that mitigates the cold start problem while maintaining strong performance across various data levels. By initially applying TypiClust for diversity sampling and subsequently transitioning to uncertainty sampling with Margin, our approach effectively combines the strengths of both strategies. Our experiments demonstrate that TCM consistently outperforms existing methods across various datasets in both low and high data regimes.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningDiversitySimilar Papers 제목 키워드 기반
VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
Although pre-trained Vision-Language-Action (VLA) models exhibit impressive generalization in robotic manipulation, post-training remains crucial to ensure reliable performance during deployment. However, standard offlin…
Reinforcement LearningSelf-supervised Assisted Active Learning for Skin Lesion Segmentation
Label scarcity has been a long-standing issue for biomedical image segmentation, due to high annotation costs and professional requirements. Recently, active learning (AL) strategies strive to reduce annotation costs by …
Active LearningDiversityImage SegmentationLesion Segmentation+4Hierarchical Semi-Supervised Active Learning for Remote Sensing
The performance of deep learning models in remote sensing (RS) strongly depends on the availability of high-quality labeled data. However, collecting large-scale annotations is costly and time-consuming, while vast amoun…
Scene ClassificationActive LearningSample Efficient Robot Learning in Supervised Effect Prediction Tasks
In self-supervised robotic learning, agents acquire data through active interaction with their environment, incurring costs such as energy use, human oversight, and experimental time. To mitigate these, sample-efficient …
Active LearningDiversityEfficient ExplorationPrediction+1Exploring Spatial Diversity for Region-based Active Learning
State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level p…
Semantic SegmentationActive Learning