Adopting a human developmental visual diet yields robust, shape-based AI vision
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917323751817216 |
|---|---|
| author | Lu, Zejin Thorat, Sushrut Cichy, Radoslaw M Kietzmann, Tim C |
| author_facet | Lu, Zejin Thorat, Sushrut Cichy, Radoslaw M Kietzmann, Tim C |
| contents | Despite years of research and the dramatic scaling of artificial intelligence (AI) systems, a striking misalignment between artificial and human vision persists. Contrary to humans, AI relies heavily on texture-features rather than shape information, lacks robustness to image distortions, remains highly vulnerable to adversarial attacks, and struggles to recognise simple abstract shapes within complex backgrounds. To close this gap, here we take inspiration from how human vision develops from early infancy into adulthood. We quantified visual maturation by synthesising decades of research into a novel developmental visual diet (DVD) for AI vision. Guiding AI systems through this human-inspired curriculum, which considers the development of visual acuity, contrast sensitivity, and colour, produces models that better align with human behaviour on every hallmark of robust vision tested, yielding the strongest reported reliance on shape information to date, abstract shape recognition beyond the state of the art, and higher resilience to image corruptions and adversarial attacks. Our results thus demonstrate that robust AI vision can be achieved by guiding how a model learns, not merely how much it learns, offering a resource-efficient route toward safer and more human-like artificial visual systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_03168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adopting a human developmental visual diet yields robust, shape-based AI vision Lu, Zejin Thorat, Sushrut Cichy, Radoslaw M Kietzmann, Tim C Machine Learning Computer Vision and Pattern Recognition Despite years of research and the dramatic scaling of artificial intelligence (AI) systems, a striking misalignment between artificial and human vision persists. Contrary to humans, AI relies heavily on texture-features rather than shape information, lacks robustness to image distortions, remains highly vulnerable to adversarial attacks, and struggles to recognise simple abstract shapes within complex backgrounds. To close this gap, here we take inspiration from how human vision develops from early infancy into adulthood. We quantified visual maturation by synthesising decades of research into a novel developmental visual diet (DVD) for AI vision. Guiding AI systems through this human-inspired curriculum, which considers the development of visual acuity, contrast sensitivity, and colour, produces models that better align with human behaviour on every hallmark of robust vision tested, yielding the strongest reported reliance on shape information to date, abstract shape recognition beyond the state of the art, and higher resilience to image corruptions and adversarial attacks. Our results thus demonstrate that robust AI vision can be achieved by guiding how a model learns, not merely how much it learns, offering a resource-efficient route toward safer and more human-like artificial visual systems. |
| title | Adopting a human developmental visual diet yields robust, shape-based AI vision |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.03168 |