Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917772519276544 |
|---|---|
| author | Hao, Tianxiang Lyu, Mengyao Chen, Hui Zhao, Sicheng Ding, Xiaohan Han, Jungong Ding, Guiguang |
| author_facet | Hao, Tianxiang Lyu, Mengyao Chen, Hui Zhao, Sicheng Ding, Xiaohan Han, Jungong Ding, Guiguang |
| contents | With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a pivotal topic, particularly in data-scarce environments. Recently, parameter-efficient fine-tuning approaches, especially prompt tuning, have garnered considerable attention. To better understand the nature of prompt tuning, we propose the concept of ``Information Density'' (ID) to indicate whether a matrix strongly belongs to certain feature spaces rather than being evenly distributed across various feature spaces. We suppose a higher ID with strong bias across some feature spaces naturally leads to excellent robustness and stability. Our research, inspired by the observation that generalizability is closely linked to the information density of the prompt matrix, introduces the Dense Information Prompt (DIP). DIP aims to enhance information density to improve generalization. Furthermore, DIP significantly reduces the number of tunable parameters and the requisite storage space, making it particularly advantageous in resource-constrained settings. Comprehensive experiments substantiate the superiority of DIP. Notably, DIP surpasses the latest state-of-the-art methods by a substantial margin with an exceptionally small parameter count. Across a range of tasks spanning 11 datasets, DIP improves the average downstream accuracy of classic prompt tuning by up to 5.76% using merely 0.5K parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_10813 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability Hao, Tianxiang Lyu, Mengyao Chen, Hui Zhao, Sicheng Ding, Xiaohan Han, Jungong Ding, Guiguang Computer Vision and Pattern Recognition Computation and Language Machine Learning With the advancement of large pre-trained vision-language models, effectively transferring the knowledge embedded within these foundational models to downstream tasks has become a pivotal topic, particularly in data-scarce environments. Recently, parameter-efficient fine-tuning approaches, especially prompt tuning, have garnered considerable attention. To better understand the nature of prompt tuning, we propose the concept of ``Information Density'' (ID) to indicate whether a matrix strongly belongs to certain feature spaces rather than being evenly distributed across various feature spaces. We suppose a higher ID with strong bias across some feature spaces naturally leads to excellent robustness and stability. Our research, inspired by the observation that generalizability is closely linked to the information density of the prompt matrix, introduces the Dense Information Prompt (DIP). DIP aims to enhance information density to improve generalization. Furthermore, DIP significantly reduces the number of tunable parameters and the requisite storage space, making it particularly advantageous in resource-constrained settings. Comprehensive experiments substantiate the superiority of DIP. Notably, DIP surpasses the latest state-of-the-art methods by a substantial margin with an exceptionally small parameter count. Across a range of tasks spanning 11 datasets, DIP improves the average downstream accuracy of classic prompt tuning by up to 5.76% using merely 0.5K parameters. |
| title | Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability |
| topic | Computer Vision and Pattern Recognition Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2312.10813 |