Learning to see stuff
- Date: Mar 13, 2023
- Time: 02:00 PM c.t. - 03:00 PM (Local Time Germany)
- Speaker: Prof. Dr. Roland W. Fleming
- Kurt Koffka Professor of Experimental Psychology, Department of Psychology, Giessen University
- Location: Max-Planck-Ring 8
- Room: room 203 + zoom
- Host: Zhaoping Li (Junhao Liang)
- Contact: maria.pavlovic@tuebingen.mpg.de
Humans are very good at visually recognizing materials and inferring
their properties. Without touching surfaces, we can usually tell what
they would feel like, and we enjoy vivid visual intuitions about how
they typically behave. This is impressive because the retinal image that
the visual system receives as input is the result of complex
interactions between many physical processes. Somehow the brain has to
disentangle these different factors. I will present some recent work in
which we show that an unsupervised neural network trained on images of
surfaces spontaneously learns to disentangle reflectance, lighting and
shape. However, the disentanglement is not perfect, and we find that as a
result the network not only predicts the broad successes of human gloss
perception, but also the specific pattern of errors that humans exhibit
on an image-by-image basis. I will argue this has important
implications for thinking about appearance and vision more broadly.