Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. MIT Open Access Articles
  3. MIT Open Access Articles
  4. The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex

The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex

Thumbnail Image
Download
Name

Leibo-2015-The Invariance Hypot.pdf

Size

2.04 MB

Format

Adobe PDF

Checksum (MD5)

4c1fe1d1c2151f7b87d064d226497f2e

Author(s)
Leibo, Joel Z.
•
Liao, Qianli
•
Anselmi, Fabio
•
Poggio, Tomaso A.
Date Issued
October 2015
Journal
PLOS Computational Biology
Publisher
Public Library of Science
Citation
Leibo, Joel Z., Qianli Liao, Fabio Anselmi, and Tomaso Poggio. “The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex.” Edited by Nikolaus Kriegeskorte. PLOS Computational Biology 11, no. 10 (October 23, 2015): e1004390.
Version
Final published version
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 in agreement with the available data. The result is a unifying account linking the large literature on view-based recognition with the wealth of experimental evidence concerning domain-specific regions.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
McGovern Institute for Brain Research at MIT
Terms of Use
Creative Commons Attribution
http://creativecommons.org/licenses/by/4.0/
Persistent DSpace Link
http://hdl.handle.net/1721.1/99730
DOI of Published Version
https://doi.org/10.1371/journal.pcbi.1004390
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.