Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.13507 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916745100394496 |
|---|---|
| author | Chen, Haoyang |
| author_facet | Chen, Haoyang |
| contents | Open-Set Domain Adaptation (OSDA) confronts the dual challenge of aligning known-class distributions across domains while identifying target-domain-specific unknown categories. Current approaches often fail to leverage semantic relationships between modalities and struggle with error accumulation in unknown sample detection. We propose to harness Contrastive Language-Image Pretraining (CLIP) to address these limitations through two key innovations: 1) Prompt-driven cross-domain alignment: Learnable textual prompts conditioned on domain discrepancy metrics dynamically adapt CLIP's text encoder, enabling semantic consistency between source and target domains without explicit unknown-class supervision. 2) Gradient-aware open-set separation: A gradient analysis module quantifies domain shift by comparing the L2-norm of gradients from the learned prompts, where known/unknown samples exhibit statistically distinct gradient behaviors. Evaluations on Office-Home show that our method consistently outperforms CLIP baseline and standard baseline. Ablation studies confirm the gradient norm's critical role. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_13507 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Open Set Domain Adaptation with Vision-language models via Gradient-aware Separation Chen, Haoyang Machine Learning Computer Vision and Pattern Recognition Open-Set Domain Adaptation (OSDA) confronts the dual challenge of aligning known-class distributions across domains while identifying target-domain-specific unknown categories. Current approaches often fail to leverage semantic relationships between modalities and struggle with error accumulation in unknown sample detection. We propose to harness Contrastive Language-Image Pretraining (CLIP) to address these limitations through two key innovations: 1) Prompt-driven cross-domain alignment: Learnable textual prompts conditioned on domain discrepancy metrics dynamically adapt CLIP's text encoder, enabling semantic consistency between source and target domains without explicit unknown-class supervision. 2) Gradient-aware open-set separation: A gradient analysis module quantifies domain shift by comparing the L2-norm of gradients from the learned prompts, where known/unknown samples exhibit statistically distinct gradient behaviors. Evaluations on Office-Home show that our method consistently outperforms CLIP baseline and standard baseline. Ablation studies confirm the gradient norm's critical role. |
| title | Open Set Domain Adaptation with Vision-language models via Gradient-aware Separation |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.13507 |