Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 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

Part-based Quantitative Analysis for Heatmaps (2405.13264v1)

Published 22 May 2024 in cs.LG, cs.AI, and cs.CV

Abstract: Heatmaps have been instrumental in helping understand deep network decisions, and are a common approach for Explainable AI (XAI). While significant progress has been made in enhancing the informativeness and accessibility of heatmaps, heatmap analysis is typically very subjective and limited to domain experts. As such, developing automatic, scalable, and numerical analysis methods to make heatmap-based XAI more objective, end-user friendly, and cost-effective is vital. In addition, there is a need for comprehensive evaluation metrics to assess heatmap quality at a granular level.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Understanding the decisions of cnns: An in-model approach, Pattern Recognition Letters 133 (2020) 373–380.
  2. Evaluating the visualization of what a deep neural network has learned, IEEE transactions on neural networks and learning systems 28 (2016) 2660–2673.
  3. Learning deep features for discriminative localization, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2921–2929.
  4. S. Jo, I.-J. Yu, Puzzle-cam: Improved localization via matching partial and full features, in: 2021 IEEE International Conference on Image Processing (ICIP), IEEE, 2021, pp. 639–643.
  5. Sess: Saliency enhancing with scaling and sliding, in: Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XII, Springer, 2022, pp. 318–333.
  6. ” help me help the ai”: Understanding how explainability can support human-ai interaction, arXiv preprint arXiv:2210.03735 (2022).
  7. Rise: Randomized input sampling for explanation of black-box models, arXiv preprint arXiv:1806.07421 (2018).
  8. Top-down neural attention by excitation backprop, International Journal of Computer Vision 126 (2018) 1084–1102.
  9. Going denser with open-vocabulary part segmentation, arXiv preprint arXiv:2305.11173 (2023).
  10. Semantic-sam: Segment and recognize anything at any granularity, arXiv preprint arXiv:2307.04767 (2023).
  11. Deep inside convolutional networks: Visualising image classification models and saliency maps, arXiv preprint arXiv:1312.6034 (2013).
  12. Axiomatic attribution for deep networks, in: International conference on machine learning, PMLR, 2017, pp. 3319–3328.
  13. Grad-cam: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE international conference on computer vision, 2017, pp. 618–626.
  14. R. C. Fong, A. Vedaldi, Interpretable explanations of black boxes by meaningful perturbation, in: Proceedings of the IEEE international conference on computer vision, 2017, pp. 3429–3437.
  15. P. Dabkowski, Y. Gal, Real time image saliency for black box classifiers, Advances in neural information processing systems 30 (2017).
  16. Smoothgrad: removing noise by adding noise, arXiv preprint arXiv:1706.03825 (2017).
  17. Score-cam: Score-weighted visual explanations for convolutional neural networks, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, 2020, pp. 24–25.
  18. ” 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, 2016, pp. 1135–1144.
  19. The effectiveness of feature attribution methods and its correlation with automatic evaluation scores, Advances in Neural Information Processing Systems 34 (2021) 26422–26436.
  20. Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks, in: 2018 IEEE winter conference on applications of computer vision (WACV), IEEE, 2018, pp. 839–847.
  21. A unified view of gradient-based attribution methods for deep neural networks, in: NIPS 2017-Workshop on Interpreting, Explaining and Visualizing Deep Learning, ETH Zurich, 2017.
  22. Saliency map verbalization: Comparing feature importance representations from model-free and instruction-based methods, in: Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE), 2023, pp. 30–46.
  23. Towards self-explainability of deep neural networks with heatmap captioning and large-language models, arXiv preprint arXiv:2304.02202 (2023).
  24. Partimagenet: A large, high-quality dataset of parts, in: Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VIII, Springer, 2022, pp. 128–145.
  25. Detect what you can: Detecting and representing objects using holistic models and body parts, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 1971–1978.
  26. Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  27. K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556 (2014).
  28. An image is worth 16x16 words: Transformers for image recognition at scale, arXiv e-prints (2020) arXiv–2010.
  29. T. DeVries, G. W. Taylor, Improved regularization of convolutional neural networks with cutout, arXiv preprint arXiv:1708.04552 (2017).
  30. Cutmix: Regularization strategy to train strong classifiers with localizable features, in: International Conference on Computer Vision (ICCV), 2019.
  31. Striving for simplicity: The all convolutional net, in: ICLR (workshop track), 2015.
  32. What are the visual features underlying human versus machine vision?, in: Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017, pp. 2706–2714.
  33. Atoms of recognition in human and computer vision, Proceedings of the National Academy of Sciences 113 (2016) 2744–2749.
  34. Aggregated residual transformations for deep neural networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1492–1500.
  35. Random erasing data augmentation, in: Proceedings of the AAAI conference on artificial intelligence, volume 34, 2020, pp. 13001–13008.

Summary

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

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

Tweets