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

Ryan Blything, Valerio Biscione, Ivan Vankov, Casimir J.H. Ludwig, Jeffrey Bowers

Research output: Contribution to journalArticlepeer-review


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).

Original languageEnglish
Article number9
Pages (from-to)1-16
Number of pages16
JournalJournal of Vision
Issue number2
Publication statusPublished - 23 Feb 2021

Bibliographical note

Copyright 2021 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License


  • convolutional neural networks
  • global average pooling (GAP)
  • object recognition
  • translation invariance
  • translation tolerance


Dive into the research topics of 'The human visual system and CNNs can both support robust online translation tolerance following extreme displacements'. Together they form a unique fingerprint.

Cite this