mlsanityData to 7 Oct 2026

Testing the Channels of Convolutional Neural Networks

arXiv 2303.03400 ↗First posted 6 Mar 2023cs.LG cs.AI cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural networks have complex structures, and thus it is hard to understand their inner workings and ensure correctness. To understand and debug convolutional neural networks (CNNs) we propose techniques for testing the channels of CNNs. We design FtGAN, an extension to GAN, that can generate test data with varying the intensity (i.e., sum of the neurons) of a channel of a target CNN. We also proposed a channel selection algorithm to find representative channels for testing. To efficiently inspect the target CNN's inference computations, we define unexpectedness score, which estimates how similar the inference computation of the test data is to that of the training data. We evaluated FtGAN with five public datasets and showed that our techniques successfully identify defective channels in five different CNN models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 55 references that are in the map. First posted on arXiv 6 Mar 2023.

Builds on

36 of 55 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2017Improved Training of Wasserstein GANscited by 2,223
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  12. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
24 more
  1. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  2. 2017Wasserstein GANcited by 635
  3. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  4. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
  5. 2018Insights on representational similarity in neural networks with canonical correlationcited by 318
  6. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 307
  7. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  8. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  9. 2015Convergent Learning: Do different neural networks learn the same representations?cited by 215
  10. 2018Spatially Transformed Adversarial Examplescited by 195
  11. 2018DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systemscited by 144
  12. 2019SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editingcited by 93
  13. 2019Unrestricted Adversarial Examples via Semantic Manipulationcited by 84
  14. 2018TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzingcited by 67
  15. 2018Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learningcited by 56
  16. 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 56
  17. 2019RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributescited by 56
  18. 2016Regularizing CNNs with Locally Constrained Decorrelationscited by 41
  19. 2020Model-based Exploration of the Frontier of Behaviours for Deep Learning System Testingcited by 40
  20. 2018Testing Deep Neural Networkscited by 36
  21. 2020Importance-Driven Deep Learning System Testingcited by 24
  22. 2020Towards Feature Space Adversarial Attackcited by 11
  23. 2018The GAN that Warped: Semantic Attribute Editing with Unpaired Datacited by 7
  24. 2017Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributescited by 1

Built on by

Not cited yet.