Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model
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_ | 1866916313561038848 |
|---|---|
| author | Nguyen, Duy M. H. Le, An T. Nguyen, Trung Q. Diep, Nghiem T. Nguyen, Tai Duong-Tran, Duy Peters, Jan Shen, Li Niepert, Mathias Sonntag, Daniel |
| author_facet | Nguyen, Duy M. H. Le, An T. Nguyen, Trung Q. Diep, Nghiem T. Nguyen, Tai Duong-Tran, Duy Peters, Jan Shen, Li Niepert, Mathias Sonntag, Daniel |
| contents | Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data. However, existing works typically rely on optimizing unified prompt inputs, often struggling with fine-grained classification tasks due to insufficient discriminative attributes. To tackle this, we consider a new framework based on a dual context of both domain-shared and class-specific contexts, where the latter is generated by Large Language Models (LLMs) such as GPTs. Such dual prompt methods enhance the model's feature representation by joining implicit and explicit factors encoded in LLM knowledge. Moreover, we formulate the Unbalanced Optimal Transport (UOT) theory to quantify the relationships between constructed prompts and visual tokens. Through partial matching, UOT can properly align discrete sets of visual tokens and prompt embeddings under different mass distributions, which is particularly valuable for handling irrelevant or noisy elements, ensuring that the preservation of mass does not restrict transport solutions. Furthermore, UOT's characteristics integrate seamlessly with image augmentation, expanding the training sample pool while maintaining a reasonable distance between perturbed images and prompt inputs. Extensive experiments across few-shot classification and adapter settings substantiate the superiority of our model over current state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04489 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model Nguyen, Duy M. H. Le, An T. Nguyen, Trung Q. Diep, Nghiem T. Nguyen, Tai Duong-Tran, Duy Peters, Jan Shen, Li Niepert, Mathias Sonntag, Daniel Computer Vision and Pattern Recognition Prompt learning methods are gaining increasing attention due to their ability to customize large vision-language models to new domains using pre-trained contextual knowledge and minimal training data. However, existing works typically rely on optimizing unified prompt inputs, often struggling with fine-grained classification tasks due to insufficient discriminative attributes. To tackle this, we consider a new framework based on a dual context of both domain-shared and class-specific contexts, where the latter is generated by Large Language Models (LLMs) such as GPTs. Such dual prompt methods enhance the model's feature representation by joining implicit and explicit factors encoded in LLM knowledge. Moreover, we formulate the Unbalanced Optimal Transport (UOT) theory to quantify the relationships between constructed prompts and visual tokens. Through partial matching, UOT can properly align discrete sets of visual tokens and prompt embeddings under different mass distributions, which is particularly valuable for handling irrelevant or noisy elements, ensuring that the preservation of mass does not restrict transport solutions. Furthermore, UOT's characteristics integrate seamlessly with image augmentation, expanding the training sample pool while maintaining a reasonable distance between perturbed images and prompt inputs. Extensive experiments across few-shot classification and adapter settings substantiate the superiority of our model over current state-of-the-art baselines. |
| title | Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.04489 |