Space Rotation with Basis Transformation for Training-free Test-Time Adaptation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912250320650240 |
|---|---|
| author | Ding, Chenhao Gao, Xinyuan Dong, Songlin He, Yuhang Wang, Qiang Song, Xiang Kot, Alex Gong, Yihong |
| author_facet | Ding, Chenhao Gao, Xinyuan Dong, Songlin He, Yuhang Wang, Qiang Song, Xiang Kot, Alex Gong, Yihong |
| contents | With the development of visual-language models (VLM) in downstream task applications, test-time adaptation methods based on VLM have attracted increasing attention for their ability to address changes distribution in test-time. Although prior approaches have achieved some progress, they typically either demand substantial computational resources or are constrained by the limitations of the original feature space, rendering them less effective for test-time adaptation tasks. To address these challenges, we propose a training-free feature space rotation with basis transformation for test-time adaptation. By leveraging the inherent distinctions among classes, we reconstruct the original feature space and map it to a new representation, thereby enhancing the clarity of class differences and providing more effective guidance for the model during testing. Additionally, to better capture relevant information from various classes, we maintain a dynamic queue to store representative samples. Experimental results across multiple benchmarks demonstrate that our method outperforms state-of-the-art techniques in terms of both performance and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19946 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Space Rotation with Basis Transformation for Training-free Test-Time Adaptation Ding, Chenhao Gao, Xinyuan Dong, Songlin He, Yuhang Wang, Qiang Song, Xiang Kot, Alex Gong, Yihong Computer Vision and Pattern Recognition With the development of visual-language models (VLM) in downstream task applications, test-time adaptation methods based on VLM have attracted increasing attention for their ability to address changes distribution in test-time. Although prior approaches have achieved some progress, they typically either demand substantial computational resources or are constrained by the limitations of the original feature space, rendering them less effective for test-time adaptation tasks. To address these challenges, we propose a training-free feature space rotation with basis transformation for test-time adaptation. By leveraging the inherent distinctions among classes, we reconstruct the original feature space and map it to a new representation, thereby enhancing the clarity of class differences and providing more effective guidance for the model during testing. Additionally, to better capture relevant information from various classes, we maintain a dynamic queue to store representative samples. Experimental results across multiple benchmarks demonstrate that our method outperforms state-of-the-art techniques in terms of both performance and efficiency. |
| title | Space Rotation with Basis Transformation for Training-free Test-Time Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.19946 |