Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models

Hongru Zhu, Peng Tang, Jeongho Park, Soojin Park, Alan Yuille

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Most objects in the visual world are partially occluded, but humans can recognize them without difficulty. However, it remains unknown whether object recognition models like convolutional neural networks (CNNs) can handle real-world occlusion. It is also a question whether efforts to make these models robust to constant mask occlusion are effective for real-world occlusion. We test both humans and the above-mentioned computational models in a challenging task of object recognition under extreme occlusion, where target objects are heavily occluded by irrelevant real objects in real backgrounds. Our results show that human vision is very robust to extreme occlusion while CNNs are not, even with modifications to handle constant mask occlusion. This implies that the ability to handle constant mask occlusion does not entail robustness to real-world occlusion. As a comparison, we propose another computational model that utilizes object parts/subparts in a compositional manner to build robustness to occlusion. This performs significantly better than CNN-based models on our task with error patterns similar to humans. These findings suggest that testing under extreme occlusion can better reveal the robustness of visual recognition, and that the principle of composition can encourage such robustness.

Original languageEnglish
Title of host publicationProceedings of the 41st Annual Meeting of the Cognitive Science Society
Subtitle of host publicationCreativity + Cognition + Computation, CogSci 2019
PublisherThe Cognitive Science Society
Pages3213-3219
Number of pages7
ISBN (Electronic)0991196775, 9780991196777
Publication statusPublished - 2019
Event41st Annual Meeting of the Cognitive Science Society: Creativity + Cognition + Computation, CogSci 2019 - Montreal, Canada
Duration: 2019 Jul 242019 Jul 27

Publication series

NameProceedings of the 41st Annual Meeting of the Cognitive Science Society: Creativity + Cognition + Computation, CogSci 2019

Conference

Conference41st Annual Meeting of the Cognitive Science Society: Creativity + Cognition + Computation, CogSci 2019
Country/TerritoryCanada
CityMontreal
Period19/7/2419/7/27

Bibliographical note

Publisher Copyright:
© Cognitive Science Society: Creativity + Cognition + Computation, CogSci 2019.All rights reserved.

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models'. Together they form a unique fingerprint.

Cite this