TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
cs.CV, cs.AI
Submitted: 2025-04-07
Updated: 2026-09-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Deep Learning using Rectified Linear Units (ReLU)
- Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- Visual Prompt Tuning for Test-time Domain Adaptation
- Gaussian Error Linear Units (GELUs)
- Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
- Towards Stable Test-Time Adaptation in Dynamic Wild World
- AdapterFusion: Non-Destructive Task Composition for Transfer Learning
- Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
- On Pitfalls of Test-Time Adaptation
- Domain Generalization: A Survey
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