Source-Free Domain Adaptation by Optimizing Batch-Wise Cosine Similarity
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912845444153344 |
|---|---|
| author | Pathak, Harsharaj Balasubramanian, Vineeth N |
| author_facet | Pathak, Harsharaj Balasubramanian, Vineeth N |
| contents | Source-Free Domain Adaptation (SFDA) is an emerging area of research that aims to adapt a model trained on a labeled source domain to an unlabeled target domain without accessing the source data. Most of the successful methods in this area rely on the concept of neighborhood consistency but are prone to errors due to misleading neighborhood information. In this paper, we explore this approach from the point of view of learning more informative clusters and mitigating the effect of noisy neighbors using a concept called neighborhood signature, and demonstrate that adaptation can be achieved using just a single loss term tailored to optimize the similarity and dissimilarity of predictions of samples in the target domain. In particular, our proposed method outperforms existing methods in the challenging VisDA dataset while also yielding competitive results on other benchmark datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_17408 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Source-Free Domain Adaptation by Optimizing Batch-Wise Cosine Similarity Pathak, Harsharaj Balasubramanian, Vineeth N Computer Vision and Pattern Recognition Source-Free Domain Adaptation (SFDA) is an emerging area of research that aims to adapt a model trained on a labeled source domain to an unlabeled target domain without accessing the source data. Most of the successful methods in this area rely on the concept of neighborhood consistency but are prone to errors due to misleading neighborhood information. In this paper, we explore this approach from the point of view of learning more informative clusters and mitigating the effect of noisy neighbors using a concept called neighborhood signature, and demonstrate that adaptation can be achieved using just a single loss term tailored to optimize the similarity and dissimilarity of predictions of samples in the target domain. In particular, our proposed method outperforms existing methods in the challenging VisDA dataset while also yielding competitive results on other benchmark datasets. |
| title | Source-Free Domain Adaptation by Optimizing Batch-Wise Cosine Similarity |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.17408 |