Do deep neural networks suffer from crowding?
© 2017 Neural information processing systems foundation. All rights reserved. Crowding is a visual effect suffered by humans, in which an object that can be recognized in isolation can no longer be recognized when other objects, called flankers, are placed close to it. In this work, we study the eff...
Main Authors: | Volokitin, Anna (Author), Roig, Gemma (Author), Poggio, Tomaso (Author) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Center for Brains, Minds, and Machines (Contributor) |
Format: | Article |
Language: | English |
Published: |
2022-01-07T16:35:51Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Do deep neural networks suffer from crowding?
by: Poggio, Tomaso, et al.
Published: (2021) -
Eccentricity dependent deep neural networks: Modeling invariance in human vision
by: Chen, Francis X., et al.
Published: (2017) -
An Overview of Some Issues in the Theory of Deep Networks
by: Poggio, Tomaso, et al.
Published: (2022) -
An Overview of Some Issues in the Theory of Deep Networks
by: Poggio, Tomaso, et al.
Published: (2021) -
Function approximation by deep networks
by: Mhaskar, H. N., et al.
Published: (2021)