mlsanityData to 14 Oct 2026

Decomposing the Deep: Finding Class Specific Filters in Deep CNNs

arXiv 2112.07719 ↗First posted 14 Dec 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Interpretability of Deep Neural Networks has become a major area of exploration. Although these networks have achieved state of the art accuracy in many tasks, it is extremely difficult to interpret and explain their decisions. In this work we analyze the final and penultimate layers of Deep Convolutional Networks and provide an efficient method for identifying subsets of features that contribute most towards the network's decision for a class. We demonstrate that the number of such features per class is much lower in comparison to the dimension of the final layer and therefore the decision surface of Deep CNNs lies on a low dimensional manifold and is proportional to the network depth. Our methods allow to decompose the final layer into separate subspaces which is far more interpretable and has a lower computational cost as compared to the final layer of the full network.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 14 Dec 2021.

Builds on

31 of 43 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2014Going Deeper with Convolutionscited by 4,241
  9. 2016Wide Residual Networkscited by 3,070
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  11. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  12. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
19 more
  1. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  2. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  3. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  4. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  5. 2018Gradient Descent Provably Optimizes Over-parameterized Neural Networkscited by 659
  6. 2018Gradient Descent Finds Global Minima of Deep Neural Networkscited by 574
  7. 2020A Survey on Neural Network Interpretabilitycited by 291
  8. 2014The Loss Surfaces of Multilayer Networkscited by 280
  9. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
  10. 2017Interpretable Convolutional Neural Networkscited by 162
  11. 2016Generating Visual Explanationscited by 158
  12. 2019Quantization Networkscited by 153
  13. 2018Interpreting CNNs via Decision Treescited by 89
  14. 2017Interpreting CNN Knowledge via an Explanatory Graphcited by 49
  15. 2018Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compressioncited by 40
  16. 2020Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filterscited by 26
  17. 2016Do semantic parts emerge in Convolutional Neural Networks?cited by 23
  18. 2021Comprehensible Convolutional Neural Networks via Guided Concept Learningcited by 11
  19. 2016Learning Discriminative Features via Label Consistent Neural Networkcited by 4

Built on by

Not cited yet.