Source-Free Domain Adaptation with Vision-Language Prior
cs.CV
Submitted: 2026-04-20
Updated: 2026-11-06
Code: https://github.com/tntek/DIFO-Plus
Terminology
Sources
- Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning
- Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
- Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
- VisDA: The Visual Domain Adaptation Challenge
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs