Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks
This work addresses robustness issues in computer vision for real-world applications, but it is incremental as it builds on existing methods by integrating MHN without requiring test-time adaptation.
The study tackled the problem of computer vision models being vulnerable to minor perturbations like blurring by integrating Modern Hopfield Networks (MHN) into baseline models, resulting in a 13.84% increase in average corruption accuracy and significant reductions in corruption error metrics on the MNIST-C dataset.
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)