mlsanityData to 14 Oct 2026

Towards Improving Robustness Against Common Corruptions using Mixture of Class Specific Experts

arXiv 2311.10177 ↗First posted 16 Nov 2023cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural networks have demonstrated significant accuracy across various domains, yet their vulnerability to subtle input alterations remains a persistent challenge. Conventional methods like data augmentation, while effective to some extent, fall short in addressing unforeseen corruptions, limiting the adaptability of neural networks in real-world scenarios. In response, this paper introduces a novel paradigm known as the Mixture of Class-Specific Expert Architecture. The approach involves disentangling feature learning for individual classes, offering a nuanced enhancement in scalability and overall performance. By training dedicated network segments for each class and subsequently aggregating their outputs, the proposed architecture aims to mitigate vulnerabilities associated with common neural network structures. The study underscores the importance of comprehensive evaluation methodologies, advocating for the incorporation of benchmarks like the common corruptions benchmark. This inclusion provides nuanced insights into the vulnerabilities of neural networks, especially concerning their generalization capabilities and robustness to unforeseen distortions. The research aligns with the broader objective of advancing the development of highly robust learning systems capable of nuanced reasoning across diverse and challenging real-world scenarios. Through this contribution, the paper aims to foster a deeper understanding of neural network limitations and proposes a practical approach to enhance their resilience in the face of evolving and unpredictable conditions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 55 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

37 of 55 references.

References · 37

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  8. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  9. 2016Adversarial examples in the physical worldcited by 1,769
  10. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  11. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  12. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
25 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  2. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  3. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  4. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  5. 2018Disentangling by Factorisingcited by 616
  6. 2017One pixel attack for fooling deep neural networkscited by 582
  7. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  8. 2018Towards a Definition of Disentangled Representationscited by 296
  9. 2018Generalisation in humans and deep neural networkscited by 237
  10. 2018Adversarial Logit Pairingcited by 224
  11. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
  12. 2018Do CIFAR-10 Classifiers Generalize to CIFAR-10?cited by 200
  13. 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
  14. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  15. 2016Understanding How Image Quality Affects Deep Neural Networkscited by 119
  16. 2016Composing graphical models with neural networks for structured representations and fast inferencecited by 113
  17. 2017A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortionscited by 108
  18. 2017Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observationscited by 100
  19. 2016Disentangling factors of variation in deep representations using adversarial trainingcited by 87
  20. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  21. 2018Structured Disentangled Representationscited by 62
  22. 2016Defensive Distillation is Not Robust to Adversarial Examplescited by 60
  23. 2017Google's Cloud Vision API Is Not Robust To Noisecited by 37
  24. 2014Discovering Hidden Factors of Variation in Deep Networkscited by 21
  25. 2017Provably Minimally-Distorted Adversarial Examplescited by 12

Built on by

Not cited yet.