Transitive Vision-Language Prompt Learning for Domain Generalization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917652692205568 |
|---|---|
| author | Wang, Liyuan Jin, Yan Chen, Zhen Wu, Jinlin Li, Mengke Lu, Yang Wang, Hanzi |
| author_facet | Wang, Liyuan Jin, Yan Chen, Zhen Wu, Jinlin Li, Mengke Lu, Yang Wang, Hanzi |
| contents | The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains. The recent learning method based on the vision-language pre-training model is a great tool for domain generalization and can solve this problem to a large extent. However, there are still some issues that an advancement still suffers from trading-off between domain invariance and class separability, which are crucial in current DG problems. However, there are still some issues that an advancement still suffers from trading-off between domain invariance and class separability, which are crucial in current DG problems. In this paper, we introduce a novel prompt learning strategy that leverages deep vision prompts to address domain invariance while utilizing language prompts to ensure class separability, coupled with adaptive weighting mechanisms to balance domain invariance and class separability. Extensive experiments demonstrate that deep vision prompts effectively extract domain-invariant features, significantly improving the generalization ability of deep models and achieving state-of-the-art performance on three datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18758 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transitive Vision-Language Prompt Learning for Domain Generalization Wang, Liyuan Jin, Yan Chen, Zhen Wu, Jinlin Li, Mengke Lu, Yang Wang, Hanzi Computer Vision and Pattern Recognition Machine Learning The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains. The recent learning method based on the vision-language pre-training model is a great tool for domain generalization and can solve this problem to a large extent. However, there are still some issues that an advancement still suffers from trading-off between domain invariance and class separability, which are crucial in current DG problems. However, there are still some issues that an advancement still suffers from trading-off between domain invariance and class separability, which are crucial in current DG problems. In this paper, we introduce a novel prompt learning strategy that leverages deep vision prompts to address domain invariance while utilizing language prompts to ensure class separability, coupled with adaptive weighting mechanisms to balance domain invariance and class separability. Extensive experiments demonstrate that deep vision prompts effectively extract domain-invariant features, significantly improving the generalization ability of deep models and achieving state-of-the-art performance on three datasets. |
| title | Transitive Vision-Language Prompt Learning for Domain Generalization |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.18758 |