StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917788884402176 |
|---|---|
| author | Seo, Seungwon Lee, Suho Hwang, Sangheum |
| author_facet | Seo, Seungwon Lee, Suho Hwang, Sangheum |
| contents | Utilizing large-scale pretrained models is a well-known strategy to enhance performance on various target tasks. It is typically achieved through fine-tuning pretrained models on target tasks. However, na\"ıve fine-tuning may not fully leverage knowledge embedded in pretrained models. In this study, we introduce a novel fine-tuning method, called stochastic cross-attention (StochCA), specific to Transformer architectures. This method modifies the Transformer's self-attention mechanism to selectively utilize knowledge from pretrained models during fine-tuning. Specifically, in each block, instead of self-attention, cross-attention is performed stochastically according to the predefined probability, where keys and values are extracted from the corresponding block of a pretrained model. By doing so, queries and channel-mixing multi-layer perceptron layers of a target model are fine-tuned to target tasks to learn how to effectively exploit rich representations of pretrained models. To verify the effectiveness of StochCA, extensive experiments are conducted on benchmarks in the areas of transfer learning and domain generalization, where the exploitation of pretrained models is critical. Our experimental results show the superiority of StochCA over state-of-the-art approaches in both areas. Furthermore, we demonstrate that StochCA is complementary to existing approaches, i.e., it can be combined with them to further improve performance. Our code is available at https://github.com/daintlab/stochastic_cross_attention |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16092 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention Seo, Seungwon Lee, Suho Hwang, Sangheum Computer Vision and Pattern Recognition Utilizing large-scale pretrained models is a well-known strategy to enhance performance on various target tasks. It is typically achieved through fine-tuning pretrained models on target tasks. However, na\"ıve fine-tuning may not fully leverage knowledge embedded in pretrained models. In this study, we introduce a novel fine-tuning method, called stochastic cross-attention (StochCA), specific to Transformer architectures. This method modifies the Transformer's self-attention mechanism to selectively utilize knowledge from pretrained models during fine-tuning. Specifically, in each block, instead of self-attention, cross-attention is performed stochastically according to the predefined probability, where keys and values are extracted from the corresponding block of a pretrained model. By doing so, queries and channel-mixing multi-layer perceptron layers of a target model are fine-tuned to target tasks to learn how to effectively exploit rich representations of pretrained models. To verify the effectiveness of StochCA, extensive experiments are conducted on benchmarks in the areas of transfer learning and domain generalization, where the exploitation of pretrained models is critical. Our experimental results show the superiority of StochCA over state-of-the-art approaches in both areas. Furthermore, we demonstrate that StochCA is complementary to existing approaches, i.e., it can be combined with them to further improve performance. Our code is available at https://github.com/daintlab/stochastic_cross_attention |
| title | StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.16092 |