mlsanityData to 7 Oct 2026

Improving Robustness of Deep Convolutional Neural Networks via Multiresolution Learning

arXiv 2309.13752 ↗First posted 24 Sep 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The current learning process of deep learning, regardless of any deep neural network (DNN) architecture and/or learning algorithm used, is essentially a single resolution training. We explore multiresolution learning and show that multiresolution learning can significantly improve robustness of DNN models for both 1D signal and 2D signal (image) prediction problems. We demonstrate this improvement in terms of both noise and adversarial robustness as well as with small training dataset size. Our results also suggest that it may not be necessary to trade standard accuracy for robustness with multiresolution learning, which is, interestingly, contrary to the observation obtained from the traditional single resolution learning setting.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 39 references that are in the map. First posted on arXiv 24 Sep 2023.

Builds on

19 of 39 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  4. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  5. 2018Robustness May Be at Odds with Accuracycited by 873
  6. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  7. 2017One pixel attack for fooling deep neural networkscited by 579
  8. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  9. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  10. 2021Data Augmentation Can Improve Robustnesscited by 193
  11. 2017Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CTcited by 87
  12. 2019When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attackscited by 87
7 more
  1. 2016Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classificationcited by 84
  2. 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
  3. 2019Multi-level Wavelet Convolutional Neural Networkscited by 59
  4. 2015A Unified Gradient Regularization Family for Adversarial Examplescited by 43
  5. 2020Neural networks with late-phase weightscited by 29
  6. 2017DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samplescited by 22
  7. 2016Convolution in Convolution for Network in Networkcited by 9

Built on by

Not cited yet.