Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.10273 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918325474295808 |
|---|---|
| author | Sun, Haoran Wang, Bingyang Yu, Suyang Li, Yijiang Gao, Qingying Lyu, Haiyun Huang, Lianyu Hong, Zelong Ge, Jiahui Ma, Qianli He, Hang Zhou, Yifan Guo, Lingzi Mei, Lantao Wang, Maijunxian Luo, Dezhi Deng, Hokin |
| author_facet | Sun, Haoran Wang, Bingyang Yu, Suyang Li, Yijiang Gao, Qingying Lyu, Haiyun Huang, Lianyu Hong, Zelong Ge, Jiahui Ma, Qianli He, Hang Zhou, Yifan Guo, Lingzi Mei, Lantao Wang, Maijunxian Luo, Dezhi Deng, Hokin |
| contents | Perceptual constancy is the ability to maintain stable perceptions of objects despite changes in sensory input, such as variations in distance, angle, or lighting. This ability is crucial for visual understanding in a dynamic world. Here, we explored such ability in current Vision Language Models (VLMs). In this study, we evaluated 155 VLMs using 236 experiments across three domains: color, size, and shape constancy. The experiments included single-image and video adaptations of classic cognitive tasks, along with novel tasks in in-the-wild conditions. We found significant variability in VLM performance across these domains, with model performance in shape constancy clearly dissociated from that of color and size constancy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10273 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Probing Perceptual Constancy in Large Vision-Language Models Sun, Haoran Wang, Bingyang Yu, Suyang Li, Yijiang Gao, Qingying Lyu, Haiyun Huang, Lianyu Hong, Zelong Ge, Jiahui Ma, Qianli He, Hang Zhou, Yifan Guo, Lingzi Mei, Lantao Wang, Maijunxian Luo, Dezhi Deng, Hokin Computer Vision and Pattern Recognition Artificial Intelligence Perceptual constancy is the ability to maintain stable perceptions of objects despite changes in sensory input, such as variations in distance, angle, or lighting. This ability is crucial for visual understanding in a dynamic world. Here, we explored such ability in current Vision Language Models (VLMs). In this study, we evaluated 155 VLMs using 236 experiments across three domains: color, size, and shape constancy. The experiments included single-image and video adaptations of classic cognitive tasks, along with novel tasks in in-the-wild conditions. We found significant variability in VLM performance across these domains, with model performance in shape constancy clearly dissociated from that of color and size constancy. |
| title | Probing Perceptual Constancy in Large Vision-Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.10273 |