mlsanityData to 14 Oct 2026

Easy Batch Normalization

arXiv 2207.08940 ↗First posted 18 Jul 2022cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

It was shown that adversarial examples improve object recognition. But what about their opposite side, easy examples? Easy examples are samples that the machine learning model classifies correctly with high confidence. In our paper, we are making the first step toward exploring the potential benefits of using easy examples in the training procedure of neural networks. We propose to use an auxiliary batch normalization for easy examples for the standard and robust accuracy improvement.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 20 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

18 of 20 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  7. 2017A Closer Look at Memorization in Deep Networkscited by 942
  8. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  9. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  10. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  11. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 336
  12. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
6 more
  1. 2019Adversarial Examples Improve Image Recognitioncited by 286
  2. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 182
  3. 2021The Low-Rank Simplicity Bias in Deep Networkscited by 154
  4. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  5. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  6. 2019Empirical Study of Easy and Hard Examples in CNN Trainingcited by 9

Built on by

Not cited yet.