Papers
Topics
Authors
Recent
Search
2000 character limit reached

Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Models

Published 3 Apr 2024 in cs.CV and cs.AI | (2404.02618v1)

Abstract: We present DiffExplainer, a novel framework that, leveraging language-vision models, enables multimodal global explainability. DiffExplainer employs diffusion models conditioned on optimized text prompts, synthesizing images that maximize class outputs and hidden features of a classifier, thus providing a visual tool for explaining decisions. Moreover, the analysis of generated visual descriptions allows for automatic identification of biases and spurious features, as opposed to traditional methods that often rely on manual intervention. The cross-modal transferability of language-vision models also enables the possibility to describe decisions in a more human-interpretable way, i.e., through text. We conduct comprehensive experiments, which include an extensive user study, demonstrating the effectiveness of DiffExplainer on 1) the generation of high-quality images explaining model decisions, surpassing existing activation maximization methods, and 2) the automated identification of biases and spurious features.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Salient imagenet: How to discover spurious features in deep learning? In International Conference on Learning Representations, 2022.
  2. Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In International Conference on Learning Representations, 2019.
  3. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. In International Conference on Learning Representations (ICLR), 2020.
  4. Wilds: A benchmark of in-the-wild distribution shifts. In International Conference on Machine Learning, pages 5637–5664. PMLR, 2021.
  5. {BREEDS}: Benchmarks for subpopulation shift. In International Conference on Learning Representations, 2021.
  6. Freeze then train: Towards provable representation learning under spurious correlations and feature noise. In Francisco Ruiz, Jennifer Dy, and Jan-Willem van de Meent, editors, Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, volume 206 of Proceedings of Machine Learning Research, pages 8968–8990. PMLR, 25–27 Apr 2023.
  7. Grad-cam: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 618–626, 2017.
  8. Understanding failures of deep networks via robust feature extraction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 12853–12862, June 2021.
  9. "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, KDD ’16, page 1135–1144, New York, NY, USA, 2016. Association for Computing Machinery.
  10. A unified approach to interpreting model predictions. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017.
  11. Learning important features through propagating activation differences. In Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML’17, page 3145–3153. JMLR.org, 2017.
  12. Towards automatic concept-based explanations. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019.
  13. Concept bottleneck models. In Hal Daumé III and Aarti Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 5338–5348. PMLR, 13–18 Jul 2020.
  14. Missingness bias in model debugging. In International Conference on Learning Representations, 2022.
  15. Axiomatic attribution for deep networks. In Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML’17, page 3319–3328. JMLR.org, 2017.
  16. Understanding neural networks through deep visualization. CoRR, abs/1506.06579, 2015.
  17. Visualizing and understanding convolutional networks. In David Fleet, Tomas Pajdla, Bernt Schiele, and Tinne Tuytelaars, editors, Computer Vision – ECCV 2014, pages 818–833, Cham, 2014. Springer International Publishing.
  18. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In CVPR, pages 427–436. IEEE Computer Society, 2015.
  19. Synthesizing the preferred inputs for neurons in neural networks via deep generator networks. In Daniel D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett, editors, NeurIPS, pages 3387–3395, 2016.
  20. Multifaceted feature visualization: Uncovering the different types of features learned by each neuron in deep neural networks. CoRR, abs/1602.03616, 2016.
  21. Deep inside convolutional networks: Visualising image classification models and saliency maps. In Yoshua Bengio and Yann LeCun, editors, ICLR (Workshop Poster), 2014.
  22. Visualizing deep convolutional neural networks using natural pre-images. International Journal of Computer Vision, pages 1–23, 2016.
  23. Don’t take the easy way out: Ensemble based methods for avoiding known dataset biases. In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan, editors, EMNLP/IJCNLP (1), pages 4067–4080. Association for Computational Linguistics, 2019.
  24. Environment inference for invariant learning. In International Conference on Machine Learning, pages 2189–2200. PMLR, 2021.
  25. No subclass left behind: fine-grained robustness in coarse-grained classification problems. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS’20, Red Hook, NY, USA, 2020. Curran Associates Inc.
  26. Unsupervised learning of debiased representations with pseudo-attributes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 16742–16751, June 2022.
  27. FINDING AND FIXING SPURIOUS PATTERNS WITH EXPLANATIONS, 2022.
  28. Meaningfully debugging model mistakes using conceptual counterfactual explanations. In ICML, 2021.
  29. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10684–10695, June 2022.
  30. Denoising diffusion probabilistic models. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 6840–6851. Curran Associates, Inc., 2020.
  31. Learning transferable visual models from natural language supervision. In ICML, 2021.
  32. Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378, 2023.
  33. Lcm-lora: A universal stable-diffusion acceleration module. arXiv preprint arXiv:2311.05556, 2023.
  34. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499, 2023.
  35. Segment anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 4015–4026, October 2023.
  36. Fairface: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 1548–1558, January 2021.
  37. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM International Conference on Multimedia, MM ’14, page 675–678, New York, NY, USA, 2014. Association for Computing Machinery.
  38. Understanding neural networks through deep visualization, 2015.
  39. The concrete distribution: A continuous relaxation of discrete random variables. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net, 2017.

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

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

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

Continue Learning

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

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

Collections

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

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up