Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909690460372992 |
|---|---|
| author | Lin, Haiwei Imaizumi, Shoko Kiya, Hitoshi |
| author_facet | Lin, Haiwei Imaizumi, Shoko Kiya, Hitoshi |
| contents | We propose a low-rank adaptation method for training privacy-preserving vision transformer (ViT) models that efficiently freezes pre-trained ViT model weights. In the proposed method, trainable rank decomposition matrices are injected into each layer of the ViT architecture, and moreover, the patch embedding layer is not frozen, unlike in the case of the conventional low-rank adaptation methods. The proposed method allows us not only to reduce the number of trainable parameters but to also maintain almost the same accuracy as that of full-time tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11943 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification Lin, Haiwei Imaizumi, Shoko Kiya, Hitoshi Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition We propose a low-rank adaptation method for training privacy-preserving vision transformer (ViT) models that efficiently freezes pre-trained ViT model weights. In the proposed method, trainable rank decomposition matrices are injected into each layer of the ViT architecture, and moreover, the patch embedding layer is not frozen, unlike in the case of the conventional low-rank adaptation methods. The proposed method allows us not only to reduce the number of trainable parameters but to also maintain almost the same accuracy as that of full-time tuning. |
| title | Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification |
| topic | Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.11943 |