Saved in:
Bibliographic Details
Main Authors: Sargolzaei, Saleh, Rueda, Luis
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.11309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909292890685440
author Sargolzaei, Saleh
Rueda, Luis
author_facet Sargolzaei, Saleh
Rueda, Luis
contents This study explores the potential of Modern Hopfield Networks (MHN) in improving the ability of computer vision models to handle out-of-distribution data. While current computer vision models can generalize to unseen samples from the same distribution, they are susceptible to minor perturbations such as blurring, which limits their effectiveness in real-world applications. We suggest integrating MHN into the baseline models to enhance their robustness. This integration can be implemented during the test time for any model and combined with any adversarial defense method. Our research shows that the proposed integration consistently improves model performance on the MNIST-C dataset, achieving a state-of-the-art increase of 13.84% in average corruption accuracy, a 57.49% decrease in mean Corruption Error (mCE), and a 60.61% decrease in relative mCE compared to the baseline model. Additionally, we investigate the capability of MHN to converge to the original non-corrupted data. Notably, our method does not require test-time adaptation or augmentation with corruptions, underscoring its practical viability for real-world deployment. (Source code publicly available at: https://github.com/salehsargolzaee/Hopfield-integrated-test)
format Preprint
id arxiv_https___arxiv_org_abs_2408_11309
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks
Sargolzaei, Saleh
Rueda, Luis
Computer Vision and Pattern Recognition
Machine Learning
This study explores the potential of Modern Hopfield Networks (MHN) in improving the ability of computer vision models to handle out-of-distribution data. While current computer vision models can generalize to unseen samples from the same distribution, they are susceptible to minor perturbations such as blurring, which limits their effectiveness in real-world applications. We suggest integrating MHN into the baseline models to enhance their robustness. This integration can be implemented during the test time for any model and combined with any adversarial defense method. Our research shows that the proposed integration consistently improves model performance on the MNIST-C dataset, achieving a state-of-the-art increase of 13.84% in average corruption accuracy, a 57.49% decrease in mean Corruption Error (mCE), and a 60.61% decrease in relative mCE compared to the baseline model. Additionally, we investigate the capability of MHN to converge to the original non-corrupted data. Notably, our method does not require test-time adaptation or augmentation with corruptions, underscoring its practical viability for real-world deployment. (Source code publicly available at: https://github.com/salehsargolzaee/Hopfield-integrated-test)
title Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2408.11309