Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DXAI: Explaining Classification by Image Decomposition (2401.00320v2)

Published 30 Dec 2023 in cs.CV and cs.LG

Abstract: We propose a new way to explain and to visualize neural network classification through a decomposition-based explainable AI (DXAI). Instead of providing an explanation heatmap, our method yields a decomposition of the image into class-agnostic and class-distinct parts, with respect to the data and chosen classifier. Following a fundamental signal processing paradigm of analysis and synthesis, the original image is the sum of the decomposed parts. We thus obtain a radically different way of explaining classification. The class-agnostic part ideally is composed of all image features which do not posses class information, where the class-distinct part is its complementary. This new visualization can be more helpful and informative in certain scenarios, especially when the attributes are dense, global and additive in nature, for instance, when colors or textures are essential for class distinction. Code is available at https://github.com/dxai2024/dxai.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on signal processing, 54(11):4311–4322, 2006.
  2. A survey of visual analytics for explainable artificial intelligence methods. Computers & Graphics, 102:502–520, 2022.
  3. Dual norms and image decomposition models. International journal of computer vision, 63:85–104, 2005.
  4. Structure-texture image decomposition—modeling, algorithms, and parameter selection. International journal of computer vision, 67:111–136, 2006.
  5. Layer-wise relevance propagation for neural networks with local renormalization layers. In Artificial Neural Networks and Machine Learning–ICANN 2016: 25th International Conference on Artificial Neural Networks, Barcelona, Spain, September 6-9, 2016, Proceedings, Part II 25, pages 63–71. Springer, 2016.
  6. Analysis of branch specialization and its application in image decomposition. arXiv preprint arXiv:2206.05810, 2022.
  7. Controlstyle: Text-driven stylized image generation using diffusion priors. In Proceedings of the 31st ACM International Conference on Multimedia, pages 7540–7548, 2023.
  8. Stargan v2: Diverse image synthesis for multiple domains. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020.
  9. Ingrid Daubechies. Ten lectures on wavelets. SIAM, 1992.
  10. Stable recovery of sparse overcomplete representations in the presence of noise. IEEE Transactions on information theory, 52(1):6–18, 2005.
  11. Explainable ai (xai): Core ideas, techniques, and solutions. ACM Computing Surveys, 55(9):1–33, 2023.
  12. Image decomposition and separation using sparse representations: An overview. Proceedings of the IEEE, 98(6):983–994, 2009.
  13. The false hope of current approaches to explainable artificial intelligence in health care. The Lancet Digital Health, 3(11):e745–e750, 2021.
  14. Learning visual explanations for dcnn-based image classifiers using an attention mechanism. In European Conference on Computer Vision, pages 396–411. Springer, 2022.
  15. Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14, pages 87–102. Springer, 2016.
  16. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  17. Diffusion models for counterfactual explanations. In Proceedings of the Asian Conference on Computer Vision, pages 858–876, 2022.
  18. Explainable image classification: The journey so far and the road ahead. AI, 4(3):620–651, 2023.
  19. Captum: A unified and generic model interpretability library for pytorch, 2020.
  20. Towards evaluating explanations of vision transformers for medical imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3725–3731, 2023.
  21. Influence-directed explanations for deep convolutional networks. In 2018 IEEE international test conference (ITC), pages 1–8. IEEE, 2018.
  22. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017.
  23. Stephane G Mallat. A theory for multiresolution signal decomposition: the wavelet representation. IEEE transactions on pattern analysis and machine intelligence, 11(7):674–693, 1989.
  24. But are you sure? an uncertainty-aware perspective on explainable ai. In International Conference on Artificial Intelligence and Statistics, pages 7375–7391. PMLR, 2023.
  25. The multimodal brain tumor image segmentation benchmark (brats). IEEE transactions on medical imaging, 34(10):1993–2024, 2014.
  26. Ganterfactual—counterfactual explanations for medical non-experts using generative adversarial learning. Frontiers in artificial intelligence, 5:825565, 2022.
  27. ” why should i trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144, 2016.
  28. Evaluating the visualization of what a deep neural network has learned. IEEE transactions on neural networks and learning systems, 28(11):2660–2673, 2016.
  29. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626, 2017.
  30. Axiomatic attribution for deep networks. In International conference on machine learning, pages 3319–3328. PMLR, 2017.
  31. Dang Thi Phuong Chung and Dinh Van Tai. A fruits recognition system based on a modern deep learning technique. In Journal of physics: conference series, page 012050. IOP Publishing, 2019.
  32. Explainable image classification with evidence counterfactual. Pattern Analysis and Applications, 25(2):315–335, 2022.
  33. Stylediffusion: Controllable disentangled style transfer via diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 7677–7689, 2023.
  34. Dota: A large-scale dataset for object detection in aerial images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3974–3983, 2018.
  35. Protopformer: Concentrating on prototypical parts in vision transformers for interpretable image recognition. arXiv preprint arXiv:2208.10431, 2022.
  36. Zero-shot contrastive loss for text-guided diffusion image style transfer. arXiv preprint arXiv:2303.08622, 2023.
  37. Explainable machine learning in image classification models: An uncertainty quantification perspective. Knowledge-Based Systems, 243:108418, 2022.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - dxai2024/dxai (1 star)