Large Language Models are Good Prompt Learners for Low-Shot Image Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929301048262656 |
|---|---|
| author | Zheng, Zhaoheng Wei, Jingmin Hu, Xuefeng Zhu, Haidong Nevatia, Ram |
| author_facet | Zheng, Zhaoheng Wei, Jingmin Hu, Xuefeng Zhu, Haidong Nevatia, Ram |
| contents | Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL models generate text features from the class names that only have confined class-specific information. Large Language Models (LLMs), with their vast encyclopedic knowledge, emerge as the complement. Thus, in this paper, we discuss the integration of LLMs to enhance pre-trained VL models, specifically on low-shot classification. However, the domain gap between language and vision blocks the direct application of LLMs. Thus, we propose LLaMP, Large Language Models as Prompt learners, that produces adaptive prompts for the CLIP text encoder, establishing it as the connecting bridge. Experiments show that, compared with other state-of-the-art prompt learning methods, LLaMP yields better performance on both zero-shot generalization and few-shot image classification, over a spectrum of 11 datasets. Code will be made available at: https://github.com/zhaohengz/LLaMP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_04076 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Large Language Models are Good Prompt Learners for Low-Shot Image Classification Zheng, Zhaoheng Wei, Jingmin Hu, Xuefeng Zhu, Haidong Nevatia, Ram Computer Vision and Pattern Recognition Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL models generate text features from the class names that only have confined class-specific information. Large Language Models (LLMs), with their vast encyclopedic knowledge, emerge as the complement. Thus, in this paper, we discuss the integration of LLMs to enhance pre-trained VL models, specifically on low-shot classification. However, the domain gap between language and vision blocks the direct application of LLMs. Thus, we propose LLaMP, Large Language Models as Prompt learners, that produces adaptive prompts for the CLIP text encoder, establishing it as the connecting bridge. Experiments show that, compared with other state-of-the-art prompt learning methods, LLaMP yields better performance on both zero-shot generalization and few-shot image classification, over a spectrum of 11 datasets. Code will be made available at: https://github.com/zhaohengz/LLaMP. |
| title | Large Language Models are Good Prompt Learners for Low-Shot Image Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.04076 |