Rethinking Clustering for Robustness

Motasem Alfarra, Juan C. Pérez, Adel Bibi, Ali Thabet, Pablo Arbeláez, Bernard Ghanem

Research output: Contribution to conferencePaperpeer-review


This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Training leads to robust models, whose learnt features appear to correlate with human perception. Inspired by this connection from robustness to semantics, we study the complementary connection: from semantics to robustness. To do so, we provide a robustness certificate for distance-based classification models (clustering-based classifiers). Moreover, we show that this certificate is tight, and we leverage it to propose ClusTR (Clustering Training for Robustness), a clustering-based and adversary-free training framework to learn robust models. Interestingly, ClusTR outperforms adversarially-trained networks by up to 4% under strong PGD attacks. Our code for reproducing our results can be found at

Original languageEnglish (US)
StatePublished - 2021
Event32nd British Machine Vision Conference, BMVC 2021 - Virtual, Online
Duration: Nov 22 2021Nov 25 2021


Conference32nd British Machine Vision Conference, BMVC 2021
CityVirtual, Online

Bibliographical note

Publisher Copyright:
© 2021. The copyright of this document resides with its authors.

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Rethinking Clustering for Robustness'. Together they form a unique fingerprint.

Cite this