University of Cambridge > Talks.cam > Rainbow Group Seminars > Emerging perceptual properties in foundation models: a vision science perspective

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Emerging perceptual properties in foundation models: a vision science perspective

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Yancheng Cai.

The empirical theory of vision suggests that what we see reflects statistical regularities learned through experience rather than direct representations of physical reality. Recent advances in machine learning, particularly in foundation models, have revealed intriguing parallels with human visual perception. However, the differences between biological and artificial vision systems are equally enlightening, offering unique windows into the nature of visual processing. In this talk, we will discuss how studying these artificial systems can deepen our understanding of human visual processing, while insights from vision science can guide the development of more robust and interpretable deep learning models.

Recommended papers:
  • Gomez-Villa, A., Martín, A., Vazquez-Corral, J., Bertalmío, M., & Malo, J. (2020). Color illusions also deceive CNNs for low-level vision tasks: Analysis and implications. Vision Research, 176, 156-174.
  • Hirsch, E., & Tal, A. (2020). Color visual illusions: A statistics-based computational model. Advances in neural information processing systems, 33, 9447-9458.
  • Huh, M., Cheung, B., Wang, T., & Isola, P (2023). Position: The Platonic Representation Hypothesis. In Forty-first International Conference on Machine Learning.
  • Gomez-Villa, A., Wang, K., Parraga, A. C., Twardowski, B., Malo, J., Vazquez-Corral, J., & van de Weijer, J. The Art of Deception: Color Visual Illusions and Diffusion Models. CVPR (2025).

This talk is part of the Rainbow Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Arcadia Project Seminars Zoology Graduate Seminars Education Technology

Other talks

GPU Accelerated Nested Sampling Break Elevator Pitch Talk 7 Generative AI and Diffusion Models: a Statistical Physics Analysis Share your front page Pointwise Ergodic Theorems for Amenable Groups through Random Walks
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity