Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909225616146432 |
|---|---|
| author | Xu, Zhenlin Zhu, Yi Deng, Tiffany Mittal, Abhay Chen, Yanbei Wang, Manchen Favaro, Paolo Tighe, Joseph Modolo, Davide |
| author_facet | Xu, Zhenlin Zhu, Yi Deng, Tiffany Mittal, Abhay Chen, Yanbei Wang, Manchen Favaro, Paolo Tighe, Joseph Modolo, Davide |
| contents | This paper presents novel benchmarks for evaluating vision-language models (VLMs) in zero-shot recognition, focusing on granularity and specificity. Although VLMs excel in tasks like image captioning, they face challenges in open-world settings. Our benchmarks test VLMs' consistency in understanding concepts across semantic granularity levels and their response to varying text specificity. Findings show that VLMs favor moderately fine-grained concepts and struggle with specificity, often misjudging texts that differ from their training data. Extensive evaluations reveal limitations in current VLMs, particularly in distinguishing between correct and subtly incorrect descriptions. While fine-tuning offers some improvements, it doesn't fully address these issues, highlighting the need for VLMs with enhanced generalization capabilities for real-world applications. This study provides insights into VLM limitations and suggests directions for developing more robust models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_16048 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity Xu, Zhenlin Zhu, Yi Deng, Tiffany Mittal, Abhay Chen, Yanbei Wang, Manchen Favaro, Paolo Tighe, Joseph Modolo, Davide Computer Vision and Pattern Recognition Artificial Intelligence This paper presents novel benchmarks for evaluating vision-language models (VLMs) in zero-shot recognition, focusing on granularity and specificity. Although VLMs excel in tasks like image captioning, they face challenges in open-world settings. Our benchmarks test VLMs' consistency in understanding concepts across semantic granularity levels and their response to varying text specificity. Findings show that VLMs favor moderately fine-grained concepts and struggle with specificity, often misjudging texts that differ from their training data. Extensive evaluations reveal limitations in current VLMs, particularly in distinguishing between correct and subtly incorrect descriptions. While fine-tuning offers some improvements, it doesn't fully address these issues, highlighting the need for VLMs with enhanced generalization capabilities for real-world applications. This study provides insights into VLM limitations and suggests directions for developing more robust models. |
| title | Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2306.16048 |