mlsanityData to 14 Oct 2026

Semantic interpretation for convolutional neural networks: What makes a cat a cat?

arXiv 2204.07724 ↗First posted 16 Apr 2022cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The interpretability of deep neural networks has attracted increasing attention in recent years, and several methods have been created to interpret the "black box" model. Fundamental limitations remain, however, that impede the pace of understanding the networks, especially the extraction of understandable semantic space. In this work, we introduce the framework of semantic explainable AI (S-XAI), which utilizes row-centered principal component analysis to obtain the common traits from the best combination of superpixels discovered by a genetic algorithm, and extracts understandable semantic spaces on the basis of discovered semantically sensitive neurons and visualization techniques. Statistical interpretation of the semantic space is also provided, and the concept of semantic probability is proposed for the first time. Our experimental results demonstrate that S-XAI is effective in providing a semantic interpretation for the CNN, and offers broad usage, including trustworthiness assessment and semantic sample searching.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 16 Apr 2022.

Builds on

29 of 42 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  7. 2017On Calibration of Modern Neural Networkscited by 4,960
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  11. 2017Deep Image Priorcited by 1,098
  12. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
17 more
  1. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  2. 2013Network In Networkcited by 605
  3. 2017Convolutional Sequence to Sequence Learningcited by 552
  4. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  5. 2015Recent Advances in Convolutional Neural Networkscited by 360
  6. 2020A Survey on Neural Network Interpretabilitycited by 291
  7. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  8. 2017On Detecting Adversarial Perturbationscited by 232
  9. 2015Inverting Visual Representations with Convolutional Networkscited by 170
  10. 2017Interpretable Convolutional Neural Networkscited by 162
  11. 2018Interpreting CNNs via Decision Treescited by 89
  12. 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
  13. 2016Early Methods for Detecting Adversarial Imagescited by 36
  14. 2018Explainable Neural Networks based on Additive Index Modelscited by 33
  15. 2019Interpretable CNNs for Object Classificationcited by 17
  16. 2015Understanding deep features with computer-generated imagerycited by 13
  17. 2015Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learningcited by 4

Built on by

Not cited yet.