Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
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_ | 1866913378006466560 |
|---|---|
| author | Li, Jinhao Li, Haopeng Erfani, Sarah Feng, Lei Bailey, James Liu, Feng |
| author_facet | Li, Jinhao Li, Haopeng Erfani, Sarah Feng, Lei Bailey, James Liu, Feng |
| contents | It has recently been discovered that using a pre-trained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot performance. However, in this paper, we empirically find that the finer descriptions tend to align more effectively with local areas of the query image rather than the whole image, and then we theoretically validate this finding. Thus, we present a method called weighted visual-text cross alignment (WCA). This method begins with a localized visual prompting technique, designed to identify local visual areas within the query image. The local visual areas are then cross-aligned with the finer descriptions by creating a similarity matrix using the pre-trained VLM. To determine how well a query image aligns with each category, we develop a score function based on the weighted similarities in this matrix. Extensive experiments demonstrate that our method significantly improves zero-shot performance across various datasets, achieving results that are even comparable to few-shot learning methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02915 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models Li, Jinhao Li, Haopeng Erfani, Sarah Feng, Lei Bailey, James Liu, Feng Computer Vision and Pattern Recognition Machine Learning 68T45, 68T10 I.2.10; I.4.10 It has recently been discovered that using a pre-trained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot performance. However, in this paper, we empirically find that the finer descriptions tend to align more effectively with local areas of the query image rather than the whole image, and then we theoretically validate this finding. Thus, we present a method called weighted visual-text cross alignment (WCA). This method begins with a localized visual prompting technique, designed to identify local visual areas within the query image. The local visual areas are then cross-aligned with the finer descriptions by creating a similarity matrix using the pre-trained VLM. To determine how well a query image aligns with each category, we develop a score function based on the weighted similarities in this matrix. Extensive experiments demonstrate that our method significantly improves zero-shot performance across various datasets, achieving results that are even comparable to few-shot learning methods. |
| title | Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models |
| topic | Computer Vision and Pattern Recognition Machine Learning 68T45, 68T10 I.2.10; I.4.10 |
| url | https://arxiv.org/abs/2406.02915 |