LanDA: Language-Guided Multi-Source Domain Adaptation
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_ | 1866913209162661888 |
|---|---|
| author | Wang, Zhenbin Zhang, Lei Wang, Lituan Zhu, Minjuan |
| author_facet | Wang, Zhenbin Zhang, Lei Wang, Lituan Zhu, Minjuan |
| contents | Multi-Source Domain Adaptation (MSDA) aims to mitigate changes in data distribution when transferring knowledge from multiple labeled source domains to an unlabeled target domain. However, existing MSDA techniques assume target domain images are available, yet overlook image-rich semantic information. Consequently, an open question is whether MSDA can be guided solely by textual cues in the absence of target domain images. By employing a multimodal model with a joint image and language embedding space, we propose a novel language-guided MSDA approach, termed LanDA, based on optimal transfer theory, which facilitates the transfer of multiple source domains to a new target domain, requiring only a textual description of the target domain without needing even a single target domain image, while retaining task-relevant information. We present extensive experiments across different transfer scenarios using a suite of relevant benchmarks, demonstrating that LanDA outperforms standard fine-tuning and ensemble approaches in both target and source domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_14148 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LanDA: Language-Guided Multi-Source Domain Adaptation Wang, Zhenbin Zhang, Lei Wang, Lituan Zhu, Minjuan Computer Vision and Pattern Recognition Multi-Source Domain Adaptation (MSDA) aims to mitigate changes in data distribution when transferring knowledge from multiple labeled source domains to an unlabeled target domain. However, existing MSDA techniques assume target domain images are available, yet overlook image-rich semantic information. Consequently, an open question is whether MSDA can be guided solely by textual cues in the absence of target domain images. By employing a multimodal model with a joint image and language embedding space, we propose a novel language-guided MSDA approach, termed LanDA, based on optimal transfer theory, which facilitates the transfer of multiple source domains to a new target domain, requiring only a textual description of the target domain without needing even a single target domain image, while retaining task-relevant information. We present extensive experiments across different transfer scenarios using a suite of relevant benchmarks, demonstrating that LanDA outperforms standard fine-tuning and ensemble approaches in both target and source domains. |
| title | LanDA: Language-Guided Multi-Source Domain Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.14148 |