Do Deep Neural Networks Suffer from Crowding?
Name
CBMM-Memo-069.pdf
Size
6.47 MB
Format
Adobe PDF
Checksum (MD5)
df3c08ab64de215621f40388f99e2ba0
Author(s)
Volokitin, Anna
Roig, Gemma
Poggio, Tomaso
Date Issued
June 26, 2017
Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1706.08616
Series/Report no.
CBMM Memo Series;069
Abstract
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 effect of crowding in artificial Deep Neural Networks for object recognition. We analyze both standard deep convolutional neural networks (DCNNs) as well as a new version of DCNNs which is 1) multi-scale and 2) with size of the convolution filters change depending on the eccentricity wrt to the center of fixation. Such networks, that we call eccentricity-dependent, are a computational model of the feedforward path of the primate visual cortex. Our results reveal that the eccentricity-dependent model, trained on target objects in isolation, can recognize such targets in the presence of flankers, if the targets are near the center of the image, whereas DCNNs cannot. Also, for all tested networks, when trained on targets in isolation, we find that recognition accuracy of the networks decreases the closer the flankers are to the target and the more flankers there are. We find that visual similarity between the target and flankers also plays a role and that pooling in early layers of the network leads to more crowding. Additionally, we show that incorporating the flankers into the images of the training set does not improve performance with crowding.
Subjects
Deep Neural Networks
deep convolutional neural networks
DCNN
eccentricity-dependent
Terms of Use
Attribution-NonCommercial-ShareAlike 3.0 United States
Persistent DSpace Link
