Occlusions for effective data augmentation in image classification

Ruth Fong, Andrea Vedaldi

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

2 Scopus citations

Abstract

Deep networks for visual recognition are known to leverage ''easy to recognise'' portions of objects such as faces and distinctive texture patterns. The lack of a holistic understanding of objects may increase fragility and overfitting. In recent years, several papers have proposed to address this issue by means of occlusions as a form of data augmentation. However, successes have been limited to tasks such as weak localization and model interpretation, but no benefit was demonstrated on image classification on large-scale datasets. In this paper, we show that, by using a simple technique based on batch augmentation, occlusions as data augmentation can result in better performance on ImageNet for high-capacity models (e.g., ResNet50). We also show that varying amounts of occlusions used during training can be used to study the robustness of different neural network architectures.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4158-4166
Number of pages9
ISBN (Electronic)9781728150239
DOIs
StatePublished - Oct 2019
Externally publishedYes
Event17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
Duration: Oct 27 2019Oct 28 2019

Publication series

NameProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
Country/TerritoryKorea, Republic of
CitySeoul
Period10/27/1910/28/19

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Keywords

  • Classification
  • Computer-vision
  • Deep-learning
  • Explainability
  • Interpretability

Fingerprint

Dive into the research topics of 'Occlusions for effective data augmentation in image classification'. Together they form a unique fingerprint.

Cite this