KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification
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_ | 1866929707510923264 |
|---|---|
| author | Zhu, Yue Diao, Haiwen Gao, Shang Chen, Long Lu, Huchuan |
| author_facet | Zhu, Yue Diao, Haiwen Gao, Shang Chen, Long Lu, Huchuan |
| contents | Fine-tuning pre-trained vision models for specific tasks is a common practice in computer vision. However, this process becomes more expensive as models grow larger. Recently, parameter-efficient fine-tuning (PEFT) methods have emerged as a popular solution to improve training efficiency and reduce storage needs by tuning additional low-rank modules within pre-trained backbones. Despite their advantages, they struggle with limited representation capabilities and misalignment with pre-trained intermediate features. To address these issues, we introduce an innovative Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission (KARST) for various recognition tasks. Specifically, its multi-kernel design extends Kronecker projections horizontally and separates adaptation matrices into multiple complementary spaces, reducing parameter dependency and creating more compact subspaces. Besides, it incorporates extra learnable re-scaling factors to better align with pre-trained feature distributions, allowing for more flexible and balanced feature aggregation. Extensive experiments validate that our KARST outperforms other PEFT counterparts with a negligible inference cost due to its re-parameterization characteristics. Code is publicly available at: https://github.com/Lucenova/KARST. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06779 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification Zhu, Yue Diao, Haiwen Gao, Shang Chen, Long Lu, Huchuan Computer Vision and Pattern Recognition Artificial Intelligence Fine-tuning pre-trained vision models for specific tasks is a common practice in computer vision. However, this process becomes more expensive as models grow larger. Recently, parameter-efficient fine-tuning (PEFT) methods have emerged as a popular solution to improve training efficiency and reduce storage needs by tuning additional low-rank modules within pre-trained backbones. Despite their advantages, they struggle with limited representation capabilities and misalignment with pre-trained intermediate features. To address these issues, we introduce an innovative Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission (KARST) for various recognition tasks. Specifically, its multi-kernel design extends Kronecker projections horizontally and separates adaptation matrices into multiple complementary spaces, reducing parameter dependency and creating more compact subspaces. Besides, it incorporates extra learnable re-scaling factors to better align with pre-trained feature distributions, allowing for more flexible and balanced feature aggregation. Extensive experiments validate that our KARST outperforms other PEFT counterparts with a negligible inference cost due to its re-parameterization characteristics. Code is publicly available at: https://github.com/Lucenova/KARST. |
| title | KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.06779 |