Frequency Shortcut Learning in Neural Networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

129 Downloads (Pure)

Abstract

The generalization of neural networks is harmed by shortcut learning: the use of simple non-semantic features may prevent the networks from learning deeper semantic and task-related cues. Existing studies focus mainly on explicit shortcuts, e.g. color patches and annotated text in images, that are visually detectable and may be removed. However, there exist implicit shortcuts determined by bias or superficial statistics in the data that neural networks can easily exploit. Mitigating the learning of implicit shortcuts is challenging due to the simplicity-bias and an intrinsic difficulty in identifying them. We empirically investigate shortcut learning in the frequency domain and propose a method to identify learned frequency shortcuts based on frequency removal. We found that frequency shortcuts often correspond to textures consisting of specific frequencies. We also investigate the influence of frequency shortcuts in Out-of-Distribution (OOD) tests.
Original languageEnglish
Title of host publicationNeurIPS 2022 Workshop on Distribution Shifts
Subtitle of host publicationConnecting Methods and Applications
Number of pages6
Publication statusPublished - 2022
Event36th Annual Conference on Neural Information Processing Systems, NeurIPS 2022: Connecting Methods and Applications - New Orleans Convention Center, New Orleans, United States
Duration: 28 Nov 20229 Dec 2022
Conference number: 36
https://neurips.cc/Conferences/2022

Conference

Conference36th Annual Conference on Neural Information Processing Systems, NeurIPS 2022
Abbreviated titleNeurIPS 2022
Country/TerritoryUnited States
CityNew Orleans
Period28/11/229/12/22
Internet address

Fingerprint

Dive into the research topics of 'Frequency Shortcut Learning in Neural Networks'. Together they form a unique fingerprint.
  • DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning

    Wang, S., Brune, C., Veldhuis, R. & Strisciuglio, N., 6 Oct 2023, 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Piscataway, NJ: IEEE, p. 129-138 10 p. 10350684. (Proceedings IEEE/CVF International Conference on Computer Vision Workshops (ICCVW); vol. 2023).

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Open Access
    File
    2 Citations (Scopus)
    53 Downloads (Pure)

Cite this