Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coverage

arXiv:2610.19803 · cs.CV · Submitted 2026-10-14 · Read on arXiv

cs.CV

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: Accepted at Machine Learning Journal through ACML Journal Track 2026

Code: https://github.com/nhtm2702/WHO

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Domain Adaptation — 1× in this paper · explained in 5 episodes

Sources

• Open Set Domain Adaptation: Theoretical Bound and Algorithm
• Dirichlet-based Uncertainty Calibration for Active Domain Adaptation
• On Statistical Bias In Active Learning: How and When To Fix It
• SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation
• Weakly-Supervised Domain Adaptation with Proportion-Constrained Pseudo-Labeling
• Weakly Supervised Test-Time Domain Adaptation for Object Detection
• Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks
• Active Learning Through a Covering Lens
• Generalized Coverage for More Robust Low-Budget Active Learning
• VisDA: The Visual Domain Adaptation Challenge
• Deep Residual Learning for Image Recognition

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models