Do computational models differ systematically from human object perception?

Pramod, RT and Arun, SP (2016) Do computational models differ systematically from human object perception? In: 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), JUN 26-JUL 01, 2016, Las Vegas, NV, pp. 1601-1609.

PDF 2016_Iee_Com_Vis_Pat_Rec_1601.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Recent advances in neural networks have revolutionized computer vision, but these algorithms are still outperformed by humans. Could this performance gap be due to systematic differences between object representations in humans and machines? To answer this question we collected a large dataset of 26,675 perceived dissimilarity measurements from 2,801 visual objects across 269 human subjects, and used this dataset to train and test leading computational models. The best model (a combination of all models) accounted for 68% of the explainable variance. Importantly, all computational models showed systematic deviations from perception: (1) They underestimated perceptual distances between objects with symmetry or large area differences; (2) They overestimated perceptual distances between objects with shared features. Our results reveal critical elements missing in computer vision algorithms and point to explicit encoding of these properties in higher visual areas in the brain.

Item Type:	Conference Proceedings
Series.:	IEEE Conference on Computer Vision and Pattern Recognition
Additional Information:	29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, JUN 26-JUL 01, 2016
Department/Centre:	Division of Biological Sciences > Centre for Neuroscience Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	03 Jun 2017 09:44
Last Modified:	21 Feb 2019 10:39
URI:	http://eprints.iisc.ac.in/id/eprint/57128

Actions (login required)

View Item