Papers
Topics
Authors
Recent
Search
2000 character limit reached

Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition

Published 25 Jan 2024 in cs.CV and cs.AI | (2402.03348v2)

Abstract: The truthfulness of existing explanation methods in authentically elucidating the underlying model's decision-making process has been questioned. Existing methods have deviated from faithfully representing the model, thus susceptible to adversarial attacks. To address this, we propose a novel eXplainable AI (XAI) method called SRD (Sharing Ratio Decomposition), which sincerely reflects the model's inference process, resulting in significantly enhanced robustness in our explanations. Different from the conventional emphasis on the neuronal level, we adopt a vector perspective to consider the intricate nonlinear interactions between filters. We also introduce an interesting observation termed Activation-Pattern-Only Prediction (APOP), letting us emphasize the importance of inactive neurons and redefine relevance encapsulating all relevant information including both active and inactive neurons. Our method, SRD, allows for the recursive decomposition of a Pointwise Feature Vector (PFV), providing a high-resolution Effective Receptive Field (ERF) at any layer.

Authors (3)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Towards robust interpretability with self-explaining neural networks. Advances in neural information processing systems, 31, 2018.
  2. Towards better understanding of gradient-based attribution methods for deep neural networks. In International Conference on Learning Representations(ICLR), 2018.
  3. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one, 10(7):e0130140, 2015.
  4. Evaluating and aggregating feature-based model explanations. In Christian Bessiere (ed.), Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pp. 3016–3022. International Joint Conferences on Artificial Intelligence Organization, 2020.
  5. Shortcomings of top-down randomization-based sanity checks for evaluations of deep neural network explanations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  16143–16152, 2023.
  6. Concise explanations of neural networks using adversarial training. In International Conference on Machine Learning, pp. 1383–1391. PMLR, 2020.
  7. Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. In 2018 IEEE winter conference on applications of computer vision (WACV), pp.  839–847. IEEE, 2018.
  8. Explanations can be manipulated and geometry is to blame. Advances in neural information processing systems, 32, 2019.
  9. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608, 2017.
  10. Craft: Concept recursive activation factorization for explainability. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  2711–2721, 2023.
  11. Axiom-based grad-cam: Towards accurate visualization and explanation of cnns. In 31st British Machine Vision Conference 2020, BMVC 2020, Virtual Event, UK, September 7-10, 2020, 2020.
  12. Large-scale unsupervised semantic segmentation. IEEE transactions on pattern analysis and machine intelligence, 2022.
  13. Interpretation of neural networks is fragile. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pp.  3681–3688, 2019a.
  14. Towards automatic concept-based explanations. Advances in neural information processing systems, 32, 2019b.
  15. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  770–778, 2016.
  16. Quantus: An explainable ai toolkit for responsible evaluation of neural network explanations and beyond. Journal of Machine Learning Research, 24(34):1–11, 2023.
  17. Layercam: Exploring hierarchical class activation maps for localization. IEEE Transactions on Image Processing, 30:5875–5888, 2021.
  18. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). In International conference on machine learning, pp. 2668–2677. PMLR, 2018.
  19. Towards best practice in explaining neural network decisions with lrp. In 2020 International Joint Conference on Neural Networks (IJCNN), pp.  1–7. IEEE, 2020.
  20. Understanding the effective receptive field in deep convolutional neural networks. Advances in neural information processing systems, 29, 2016.
  21. Explaining nonlinear classification decisions with deep taylor decomposition. Pattern recognition, 65:211–222, 2017.
  22. Layer-wise relevance propagation: an overview. Explainable AI: interpreting, explaining and visualizing deep learning, pp.  193–209, 2019.
  23. Harish Guruprasad Ramaswamy et al. Ablation-cam: Visual explanations for deep convolutional network via gradient-free localization. In proceedings of the IEEE/CVF winter conference on applications of computer vision, pp.  983–991, 2020.
  24. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pp.  618–626, 2017.
  25. Very deep convolutional networks for large-scale image recognition. In Yoshua Bengio and Yann LeCun (eds.), International Conference on Learning Representations(ICLR), 2015.
  26. Deep inside convolutional networks: Visualising image classification models and saliency maps. In Workshop at International Conference on Learning Representations(ICLR), 2014.
  27. Smoothgrad: removing noise by adding noise. CoRR, abs/1706.03825, 2017.
  28. Striving for simplicity: The all convolutional net. In Workshop at International Conference on Learning Representations(ICLR), 2015.
  29. Full-gradient representation for neural network visualization. Advances in neural information processing systems, 32, 2019.
  30. Axiomatic attribution for deep networks. In International conference on machine learning, pp. 3319–3328. PMLR, 2017.
  31. Score-cam: Score-weighted visual explanations for convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp.  24–25, 2020.
  32. Top-down neural attention by excitation backprop. International Journal of Computer Vision, 126(10):1084–1102, 2018.
  33. Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  2921–2929, 2016.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 2 tweets with 3 likes about this paper.

Sign Up for Free