The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex
Name
CBMM-Memo-004.pdf
Size
2.25 MB
Format
Adobe PDF
Checksum (MD5)
413301abd5bd92eb8eb2a0bb9093d2de
Author(s)
Leibo, Joel Z
Liao, Qianli
Anselmi, Fabio
Poggio, Tomaso
Date Issued
April 26, 2015
Publisher
Center for Brains, Minds and Machines (CBMM), bioRxiv
Citation
http://dx.doi.org/10.1101/004473
Series/Report no.
CBMM Memo Series;004
Abstract
Is visual cortex made up of general-purpose information processing machinery, or does it consist of a collection of specialized modules? If prior knowledge, acquired from learning a set of objects is only transferable to new objects that share properties with the old, then the recognition system’s optimal organization must be one containing specialized modules for different object classes. Our analysis starts from a premise we call the invariance hypothesis: that the computational goal of the ventral stream is to compute an invariant-to-transformations and discriminative signature for recognition. The key condition enabling approximate transfer of invariance without sacrificing discriminability turns out to be that the learned and novel objects transform similarly. This implies that the optimal recognition system must contain subsystems trained only with data from similarly-transforming objects and suggests a novel interpretation of domain-specific regions like the fusiform face area (FFA). Furthermore, we can define an index of transformation-compatibility, computable from videos, that can be combined with information about the statistics of natural vision to yield predictions for which object categories ought to have domain-specific regions. The result is a unifying account linking the large literature on view-based recognition with the wealth of experimental evidence concerning domain-specific regions.
Subjects
Invariance
Computer vision
Machine Learning
Terms of Use
Attribution-NonCommercial 3.0 United States
Persistent DSpace Link
