November 04, 2015 16:15 - 17:15
BSI Central Building 1F Seminar Room
A glance at an object is often sufficient to recognize it and recover fine details of its shape and appearance, even under highly variable viewpoint and lighting conditions. How can vision be so rich, but at the same time fast? The analysis-by-synthesis approach to vision offers an account of the richness of our percepts, but it is typically considered too slow to explain perception in the brain. In this talk, I will propose a version of analysis-by-synthesis in the spirit of the Helmholtz machine (Dayan, et al., 1995) that can be implemented efficiently, by combining a generative model based on a realistic 3D computer graphics engine with a recognition model based on a deep convolutional network. The recognition model initializes inference in the generative model, which is then refined by brief runs of MCMC. We evaluate our approach in the domain of face recognition: it can reconstruct the approximate shape and texture of a novel face from a single view, at a level indistinguishable to humans; it accounts for human behavior in "hard" recognition tasks; and it matches neural responses in a network of face-selective brain areas.
- Open to Public
- Manabu TANIFUJI
Name: Manabu Tanifuji