Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2403.02714 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914702331740160 |
|---|---|
| author | Hou, Feng Yuan, Jin Yang, Ying Liu, Yang Zhang, Yang Zhong, Cheng Shi, Zhongchao Fan, Jianping Rui, Yong He, Zhiqiang |
| author_facet | Hou, Feng Yuan, Jin Yang, Ying Liu, Yang Zhang, Yang Zhong, Cheng Shi, Zhongchao Fan, Jianping Rui, Yong He, Zhiqiang |
| contents | Traditional cross-domain tasks, including domain adaptation and domain generalization, rely heavily on training model by source domain data. With the recent advance of vision-language models (VLMs), viewed as natural source models, the cross-domain task changes to directly adapt the pre-trained source model to arbitrary target domains equipped with prior domain knowledge, and we name this task Adaptive Domain Generalization (ADG). However, current cross-domain datasets have many limitations, such as unrealistic domains, unclear domain definitions, and the inability to fine-grained domain decomposition, which drives us to establish a novel dataset DomainVerse for ADG. Benefiting from the introduced hierarchical definition of domain shifts, DomainVerse consists of about 0.5 million images from 390 fine-grained realistic domains. With the help of the constructed DomainVerse and VLMs, we propose two methods called Domain CLIP and Domain++ CLIP for tuning-free adaptive domain generalization. Extensive and comprehensive experiments demonstrate the significance of the dataset and the effectiveness of the proposed methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_02714 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization Hou, Feng Yuan, Jin Yang, Ying Liu, Yang Zhang, Yang Zhong, Cheng Shi, Zhongchao Fan, Jianping Rui, Yong He, Zhiqiang Computer Vision and Pattern Recognition Traditional cross-domain tasks, including domain adaptation and domain generalization, rely heavily on training model by source domain data. With the recent advance of vision-language models (VLMs), viewed as natural source models, the cross-domain task changes to directly adapt the pre-trained source model to arbitrary target domains equipped with prior domain knowledge, and we name this task Adaptive Domain Generalization (ADG). However, current cross-domain datasets have many limitations, such as unrealistic domains, unclear domain definitions, and the inability to fine-grained domain decomposition, which drives us to establish a novel dataset DomainVerse for ADG. Benefiting from the introduced hierarchical definition of domain shifts, DomainVerse consists of about 0.5 million images from 390 fine-grained realistic domains. With the help of the constructed DomainVerse and VLMs, we propose two methods called Domain CLIP and Domain++ CLIP for tuning-free adaptive domain generalization. Extensive and comprehensive experiments demonstrate the significance of the dataset and the effectiveness of the proposed methods. |
| title | DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.02714 |