The human visual system and CNNs can both support robust online translation tolerance following extreme displacements


Visual translation tolerance refers to our capacity to recognize objects over a wide range of different retinal locations. Although translation is perhaps the simplest spatial transform that the visual system needs to cope with, the extent to which the human visual system can identify objects at previously unseen locations is unclear, with some studies reporting near complete invariance over 10 degrees and other reporting zero invariance at 4 degrees of visual angle. Similarly, there is confusion regarding the extent of translation tolerance in computational models of vision, as well as the degree of match between human and model performance. Here, we report a series of eye-tracking studies (total N = 70) demonstrating that novel objects trained at one retinal location can be recognized at high accuracy rates following translations up to 18 degrees. We also show that standard deep convolutional neural networks (DCNNs) support our findings when pretrained to classify another set of stimuli across a range of locations, or when a global average pooling (GAP) layer is added to produce larger receptive fields. Our findings provide a strong constraint for theories of human vision and help explain inconsistent findings previously reported with convolutional neural networks (CNNs).

Publication DOI:
Divisions: College of Health & Life Sciences > School of Psychology
College of Health & Life Sciences
Additional Information: Copyright 2021 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
Uncontrolled Keywords: convolutional neural networks,global average pooling (GAP),object recognition,translation invariance,translation tolerance,Ophthalmology,Sensory Systems
Publication ISSN: 1534-7362
Last Modified: 14 May 2024 07:22
Date Deposited: 23 Mar 2021 09:46
Full Text Link:
Related URLs: https://jov.arv ... ticleid=2772320 (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2021-02-23
Accepted Date: 2021-02-01
Authors: Blything, Ryan (ORCID Profile 0000-0003-2285-7219)
Biscione, Valerio
Vankov, Ivan
Ludwig, Casimir J.H.
Bowers, Jeffrey

Export / Share Citation


Additional statistics for this record