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

Improving the Explain-Any-Concept by Introducing Nonlinearity to the Trainable Surrogate Model (2405.11837v2)

Published 20 May 2024 in cs.CV and cs.AI

Abstract: In the evolving field of Explainable AI (XAI), interpreting the decisions of deep neural networks (DNNs) in computer vision tasks is an important process. While pixel-based XAI methods focus on identifying significant pixels, existing concept-based XAI methods use pre-defined or human-annotated concepts. The recently proposed Segment Anything Model (SAM) achieved a significant step forward to prepare automatic concept sets via comprehensive instance segmentation. Building upon this, the Explain Any Concept (EAC) model emerged as a flexible method for explaining DNN decisions. EAC model is based on using a surrogate model which has one trainable linear layer to simulate the target model. In this paper, by introducing an additional nonlinear layer to the original surrogate model, we show that we can improve the performance of the EAC model. We compare our proposed approach to the original EAC model and report improvements obtained on both ImageNet and MS COCO datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. W. Rawat and Z. Wang, “Deep convolutional neural networks for image classification: A comprehensive review,” Neural computation, vol. 29, no. 9, pp. 2352–2449, 2017.
  2. O. Sahin and S. Ozer, “Yolodrone+: Improved yolo architecture for object detection in uav images,” in 2022 30th Signal Processing and Communications Applications Conference (SIU), pp. 1–4, IEEE, 2022.
  3. C. Szegedy, A. Toshev, and D. Erhan, “Deep neural networks for object detection,” Advances in neural information processing systems, vol. 26, 2013.
  4. R. Valiente, M. Zaman, Y. P. Fallah, and S. Ozer, “Connected and autonomous vehicles in the deep learning era: A case study on computer-guided steering,” in Handbook Of Pattern Recognition And Computer Vision, pp. 365–384, World Scientific, 2020.
  5. H. E. Ilhan, S. Ozer, G. K. Kurt, and H. A. Cirpan, “Offloading deep learning empowered image segmentation from uav to edge server,” in 2021 44th International Conference on Telecommunications and Signal Processing (TSP), pp. 296–300, IEEE, 2021.
  6. S. Özer, M. Ege, and M. A. Özkanoglu, “Siamesefuse: A computationally efficient and a not-so-deep network to fuse visible and infrared images,” Pattern Recognition, vol. 129, p. 108712, 2022.
  7. F. Xu, H. Uszkoreit, Y. Du, W. Fan, D. Zhao, and J. Zhu, “Explainable ai: A brief survey on history, research areas, approaches and challenges,” in Natural Language Processing and Chinese Computing: 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9–14, 2019, Proceedings, Part II 8, pp. 563–574, Springer, 2019.
  8. J. Li, K. Kuang, L. Li, L. Chen, S. Zhang, J. Shao, and J. Xiao, “Instance-wise or class-wise? a tale of neighbor shapley for concept-based explanation,” in Proceedings of the 29th ACM International Conference on Multimedia, pp. 3664–3672, 2021.
  9. J. H.-w. Hsiao, H. H. T. Ngai, L. Qiu, Y. Yang, and C. C. Cao, “Roadmap of designing cognitive metrics for explainable artificial intelligence (xai),” arXiv preprint arXiv:2108.01737, 2021.
  10. L.-V. Herm, “Impact of explainable ai on cognitive load: Insights from an empirical study,” arXiv preprint arXiv:2304.08861, 2023.
  11. R. C. Fong and A. Vedaldi, “Interpretable explanations of black boxes by meaningful perturbation,” in Proceedings of the IEEE international conference on computer vision, pp. 3429–3437, 2017.
  12. B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, “Learning deep features for discriminative localization,” in IEEE conference on computer vision and pattern recognition, pp. 2921–2929, 2016.
  13. A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A. C. Berg, W.-Y. Lo, et al., “Segment anything,” arXiv preprint arXiv:2304.02643, 2023.
  14. A. Sun, P. Ma, Y. Yuan, and S. Wang, “Explain any concept: Segment anything meets concept-based explanation,” arXiv preprint arXiv:2305.10289, 2023.
  15. L. S. Shapley et al., “A value for n-person games,” 1953.
  16. E. Song, B. L. Nelson, and J. Staum, “Shapley effects for global sensitivity analysis: Theory and computation,” SIAM/ASA Journal on Uncertainty Quantification, vol. 4, no. 1, pp. 1060–1083, 2016.
  17. S. M. Lundberg, G. Erion, H. Chen, A. DeGrave, J. M. Prutkin, B. Nair, R. Katz, J. Himmelfarb, N. Bansal, and S.-I. Lee, “From local explanations to global understanding with explainable ai for trees,” Nature machine intelligence, vol. 2, no. 1, pp. 56–67, 2020.
  18. M. Ancona, C. Oztireli, and M. Gross, “Explaining deep neural networks with a polynomial time algorithm for shapley value approximation,” in International Conference on Machine Learning, pp. 272–281, PMLR, 2019.
  19. S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” Advances in neural information processing systems, vol. 30, 2017.
  20. I. Covert and S.-I. Lee, “Improving kernelshap: Practical shapley value estimation using linear regression,” in International Conference on Artificial Intelligence and Statistics, pp. 3457–3465, PMLR, 2021.
  21. K. Simonyan, A. Vedaldi, and A. Zisserman, “Deep inside convolutional networks: Visualising image classification models and saliency maps,” arXiv preprint arXiv:1312.6034, 2013.
  22. A. Shrikumar, P. Greenside, and A. Kundaje, “Learning important features through propagating activation differences,” in International conference on machine learning, pp. 3145–3153, PMLR, 2017.
  23. M. T. Ribeiro, S. Singh, and C. Guestrin, “" 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, pp. 1135–1144, 2016.
  24. B. Kim, M. Wattenberg, J. Gilmer, C. Cai, J. Wexler, F. Viegas, et al., “Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav),” in International conference on machine learning, pp. 2668–2677, PMLR, 2018.
  25. S. R. Dubey, S. K. Singh, and B. B. Chaudhuri, “Activation functions in deep learning: A comprehensive survey and benchmark,” Neurocomputing, 2022.
  26. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE conference on computer vision and pattern recognition, pp. 248–255, Ieee, 2009.
  27. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740–755, Springer, 2014.
  28. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016.
  29. V. Petsiuk, A. Das, and K. Saenko, “Rise: Randomized input sampling for explanation of black-box models,” arXiv preprint arXiv:1806.07421, 2018.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Mounes Zaval (1 paper)
  2. Sedat Ozer (10 papers)

Summary

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

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