mlsanityData to 14 Oct 2026

Classification-Denoising Networks

arXiv 2410.03505 ↗First posted 4 Oct 2024cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Image classification and denoising suffer from complementary issues of lack of robustness or partially ignoring conditioning information. We argue that they can be alleviated by unifying both tasks through a model of the joint probability of (noisy) images and class labels. Classification is performed with a forward pass followed by conditioning. Using the Tweedie-Miyasawa formula, we evaluate the denoising function with the score, which can be computed by marginalization and back-propagation. The training objective is then a combination of cross-entropy loss and denoising score matching loss integrated over noise levels. Numerical experiments on CIFAR-10 and ImageNet show competitive classification and denoising performance compared to reference deep convolutional classifiers/denoisers, and significantly improves efficiency compared to previous joint approaches. Our model shows an increased robustness to adversarial perturbations compared to a standard discriminative classifier, and allows for a novel interpretation of adversarial gradients as a difference of denoisers.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 58 of its 81 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

58 of 81 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  11. 2013Intriguing properties of neural networkscited by 5,155
  12. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
38 more
  1. 2022A ConvNet for the 2020scited by 3,579
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  4. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  5. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  6. 2018Group Normalizationcited by 1,524
  7. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  9. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  10. 2024VMamba: Visual State Space Modelcited by 969
  11. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 702
  12. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  13. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  14. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  15. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  16. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  17. 2021ResNet strikes back: An improved training procedure in timmcited by 368
  18. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 306
  19. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  20. 2023Generalization in diffusion models arises from geometry-adaptive harmonic representationscited by 185
  21. 2018Certified Adversarial Robustness with Additive Noisecited by 180
  22. 2023Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignmentcited by 171
  23. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  24. 2023Text-to-Image Diffusion Models are Zero-Shot Classifierscited by 143
  25. 2017A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortionscited by 108
  26. 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 108
  27. 2019Robust and interpretable blind image denoising via bias-free convolutional neural networkscited by 90
  28. 2020No MCMC for me: Amortized sampling for fast and stable training of energy-based modelscited by 64
  29. 2022Statistical Efficiency of Score Matching: The View from Isoperimetrycited by 64
  30. 2021Density Ratio Estimation via Infinitesimal Classificationcited by 61
  31. 2020Wavelet Integrated CNNs for Noise-Robust Image Classificationcited by 60
  32. 2022Testing Relational Understanding in Text-Guided Image Generationcited by 59
  33. 2023Intriguing properties of generative classifierscited by 52
  34. 2022DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Modelscited by 51
  35. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
  36. 2023Xformer: Hybrid X-Shaped Transformer for Image Denoisingcited by 37
  37. 2021JEM++: Improved Techniques for Training JEMcited by 28
  38. 2020Hybrid Discriminative-Generative Training via Contrastive Learningcited by 24

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Learning normalized image densities via dual score matchingcited by 18