domain shifts
Domain shifts occur when there is a mismatch between the training data distribution and the distribution of the data encountered during deployment. Adaptive models need to account for such shifts to maintain performance in real-world applications.
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation
- Gains: Fine-grained Federated Domain Adaptation in Open Set
- GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction
- Learning a Cross-Modal Schrödinger Bridge for Visual Domain Generalization
- OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata
- OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata
- Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation
- Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
- Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
- Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation
- Towards Generalizable Retina Vessel Segmentation with Deformable Graph Priors