mlsanityData to 14 Oct 2026

Pixel to Binary Embedding Towards Robustness for CNNs

arXiv 2206.05898 ↗First posted 13 Jun 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

There are several problems with the robustness of Convolutional Neural Networks (CNNs). For example, the prediction of CNNs can be changed by adding a small magnitude of noise to an input, and the performances of CNNs are degraded when the distribution of input is shifted by a transformation never seen during training (e.g., the blur effect). There are approaches to replace pixel values with binary embeddings to tackle the problem of adversarial perturbations, which successfully improve robustness. In this work, we propose Pixel to Binary Embedding (P2BE) to improve the robustness of CNNs. P2BE is a learnable binary embedding method as opposed to previous hand-coded binary embedding methods. P2BE outperforms other binary embedding methods in robustness against adversarial perturbations and visual corruptions that are not shown during training.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 48 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

41 of 48 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2016Wide Residual Networkscited by 3,070
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  10. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  11. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  12. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
29 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  2. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  3. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  4. 2018Robustness May Be at Odds with Accuracycited by 880
  5. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  6. 2016Universal adversarial perturbationscited by 784
  7. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  8. 2017One pixel attack for fooling deep neural networkscited by 582
  9. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  10. 2017Countering Adversarial Images using Input Transformationscited by 520
  11. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  12. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 336
  13. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  14. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 274
  15. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  16. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 238
  17. 2018Generalisation in humans and deep neural networkscited by 237
  18. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 235
  19. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 183
  20. 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
  21. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 159
  22. 2018Adversarial Attacks and Defences Competitioncited by 96
  23. 2016Examining the Impact of Blur on Recognition by Convolutional Networkscited by 58
  24. 2019Robust Local Features for Improving the Generalization of Adversarial Trainingcited by 30
  25. 2019Defending against Whitebox Adversarial Attacks via Randomized Discretizationcited by 29
  26. 2019Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagationcited by 28
  27. 2020Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Networkcited by 24
  28. 2020BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activationscited by 23
  29. 2018Towards Understanding Limitations of Pixel Discretization Against Adversarial Attackscited by 3

Built on by

Not cited yet.