A comparison between humans and AI at recognizing objects in unusual poses
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_ | 1866913674761863168 |
|---|---|
| author | Ollikka, Netta Abbas, Amro Perin, Andrea Kilpeläinen, Markku Deny, Stéphane |
| author_facet | Ollikka, Netta Abbas, Amro Perin, Andrea Kilpeläinen, Markku Deny, Stéphane |
| contents | Deep learning is closing the gap with human vision on several object recognition benchmarks. Here we investigate this gap for challenging images where objects are seen in unusual poses. We find that humans excel at recognizing objects in such poses. In contrast, state-of-the-art deep networks for vision (EfficientNet, SWAG, ViT, SWIN, BEiT, ConvNext) and state-of-the-art large vision-language models (Claude 3.5, Gemini 1.5, GPT-4) are systematically brittle on unusual poses, with the exception of Gemini showing excellent robustness in that condition. As we limit image exposure time, human performance degrades to the level of deep networks, suggesting that additional mental processes (requiring additional time) are necessary to identify objects in unusual poses. An analysis of error patterns of humans vs. networks reveals that even time-limited humans are dissimilar to feed-forward deep networks. In conclusion, our comparison reveals that humans and deep networks rely on different mechanisms for recognizing objects in unusual poses. Understanding the nature of the mental processes taking place during extra viewing time may be key to reproduce the robustness of human vision in silico. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03973 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A comparison between humans and AI at recognizing objects in unusual poses Ollikka, Netta Abbas, Amro Perin, Andrea Kilpeläinen, Markku Deny, Stéphane Computer Vision and Pattern Recognition Machine Learning Deep learning is closing the gap with human vision on several object recognition benchmarks. Here we investigate this gap for challenging images where objects are seen in unusual poses. We find that humans excel at recognizing objects in such poses. In contrast, state-of-the-art deep networks for vision (EfficientNet, SWAG, ViT, SWIN, BEiT, ConvNext) and state-of-the-art large vision-language models (Claude 3.5, Gemini 1.5, GPT-4) are systematically brittle on unusual poses, with the exception of Gemini showing excellent robustness in that condition. As we limit image exposure time, human performance degrades to the level of deep networks, suggesting that additional mental processes (requiring additional time) are necessary to identify objects in unusual poses. An analysis of error patterns of humans vs. networks reveals that even time-limited humans are dissimilar to feed-forward deep networks. In conclusion, our comparison reveals that humans and deep networks rely on different mechanisms for recognizing objects in unusual poses. Understanding the nature of the mental processes taking place during extra viewing time may be key to reproduce the robustness of human vision in silico. |
| title | A comparison between humans and AI at recognizing objects in unusual poses |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.03973 |