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

Global Counterfactual Directions (2404.12488v2)

Published 18 Apr 2024 in cs.LG, cs.AI, and cs.CV

Abstract: Despite increasing progress in development of methods for generating visual counterfactual explanations, especially with the recent rise of Denoising Diffusion Probabilistic Models, previous works consider them as an entirely local technique. In this work, we take the first step at globalizing them. Specifically, we discover that the latent space of Diffusion Autoencoders encodes the inference process of a given classifier in the form of global directions. We propose a novel proxy-based approach that discovers two types of these directions with the use of only single image in an entirely black-box manner. Precisely, g-directions allow for flipping the decision of a given classifier on an entire dataset of images, while h-directions further increase the diversity of explanations. We refer to them in general as Global Counterfactual Directions (GCDs). Moreover, we show that GCDs can be naturally combined with Latent Integrated Gradients resulting in a new black-box attribution method, while simultaneously enhancing the understanding of counterfactual explanations. We validate our approach on existing benchmarks and show that it generalizes to real-world use-cases.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (69)
  1. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695, 2022.
  2. Mastering the game of go with deep neural networks and tree search. nature, 529(7587):484–489, 2016.
  3. A foundation model for generalizable disease detection from retinal images. Nature, pages 1–8, 2023.
  4. Segment anything model for medical image analysis: An experimental study. Medical Image Analysis, 89:102918, 2023.
  5. Self-driving cars: A survey. Expert Systems with Applications, 165:113816, 2021.
  6. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023.
  7. Explainable ai methods-a brief overview. In International Workshop on Extending Explainable AI Beyond Deep Models and Classifiers, pages 13–38. Springer, 2020.
  8. Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 607–617, 2020.
  9. Counterfactual explanations without opening the black box: automated decisions and the gdpr. Harvard Journal of Law and Technology, 31(2):841–887, 2018.
  10. Judea Pearl. Causal inference in statistics: An overview. Statistics Surveys, 3(none):96 – 146, 2009.
  11. Counterfactual visual explanations. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 2376–2384. PMLR, 09–15 Jun 2019.
  12. A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence. IEEE Access, 9:11974–12001, 2021.
  13. Adversarial counterfactual visual explanations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16425–16435, 2023.
  14. Diffusion models for counterfactual explanations. In Proceedings of the Asian Conference on Computer Vision, pages 858–876, 2022.
  15. Diffusion visual counterfactual explanations. Advances in Neural Information Processing Systems, 35:364–377, 2022.
  16. K. Farid et al. Latent diffusion counterfactual explanations. arXiv, 2023.
  17. Deep unsupervised learning using nonequilibrium thermodynamics. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pages 2256–2265. PMLR, 2015.
  18. 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, 2020.
  19. Score-based generative modeling through stochastic differential equations. In International Conference on Learning Representations, 2021.
  20. Text-to-image models for counterfactual explanations: a black-box approach. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 4757–4767, 2024.
  21. O. Lang et al. Explaining in style: Training a gan to explain a classifier in stylespace. ICCV, 2021.
  22. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572, 2014.
  23. Intriguing properties of neural networks. In Yoshua Bengio and Yann LeCun, editors, 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, 2014.
  24. Interpretable counterfactual explanations guided by prototypes. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 650–665. Springer, 2021.
  25. Designing counterfactual generators using deep model inversion. Advances in Neural Information Processing Systems, 34:16873–16884, 2021.
  26. Ecinn: efficient counterfactuals from invertible neural networks. arXiv preprint arXiv:2103.13701, 2021.
  27. Sparse visual counterfactual explanations in image space. In DAGM German Conference on Pattern Recognition, pages 133–148. Springer, 2022.
  28. Generating interpretable counterfactual explanations by implicit minimisation of epistemic and aleatoric uncertainties. In International Conference on Artificial Intelligence and Statistics, pages 1756–1764. PMLR, 2021.
  29. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  30. Generative adversarial nets. Advances in neural information processing systems, 27, 2014.
  31. Explanation by progressive exaggeration. arXiv preprint arXiv:1911.00483, 2019.
  32. Saeed Khorram and Li Fuxin. Cycle-consistent counterfactuals by latent transformations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10203–10212, 2022.
  33. Beyond trivial counterfactual explanations with diverse valuable explanations. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1056–1065, 2021.
  34. Steex: steering counterfactual explanations with semantics. In European Conference on Computer Vision, pages 387–403. Springer, 2022.
  35. Ganmex: One-vs-one attributions using gan-based model explainability. In International Conference on Machine Learning, pages 9592–9602. PMLR, 2021.
  36. Generating natural adversarial examples. arXiv preprint arXiv:1710.11342, 2017.
  37. Fast diffusion-based counterfactuals for shortcut removal and generation. arXiv, 2023.
  38. J. Vendrow et al. Dataset interfaces: Diagnosing model failures using controllable counterfactual generation. arXiv, 2023.
  39. V. Prabhu et al. LANCE: Stress-testing visual models by generating language-guided counterfactual images. NeurIPS, 2023.
  40. Bridging the sim2real gap with CARE: Supervised detection adaptation with conditional alignment and reweighting. Transactions on Machine Learning Research, 2023.
  41. Kwon M. et al. Diffusion models already have a semantic latent space. ICLR, 2023.
  42. R. Hass et al. Discovering interpretable directions in the semantic latent space of diffusion models. arXiv, 2023.
  43. Y. Park et al. Understanding the latent space of diffusion models through the lens of riemannian geometry. NeurIPS, 2023.
  44. Uncovering the disentanglement capability in text-to-image diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1900–1910, June 2023.
  45. Training-free content injection using h-space in diffusion models. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 5151–5161, January 2024.
  46. Concept algebra for (score-based) text-controlled generative models. In A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural Information Processing Systems, volume 36, pages 35331–35349. Curran Associates, Inc., 2023.
  47. Diffusion autoencoders: Toward a meaningful and decodable representation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10619–10629, 2022.
  48. Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35(8):1798–1828, 2013.
  49. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  50. Deep inside convolutional networks: Visualising image classification models and saliency maps, 2014.
  51. Learning important features through propagating activation differences. In International conference on machine learning, pages 3145–3153. PMLR, 2017.
  52. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one, 10(7):e0130140, 2015.
  53. Explainable artificial intelligence (xai) 2.0: A manifesto of open challenges and interdisciplinary research directions. Information Fusion, 106:102301, June 2024.
  54. Axiomatic attribution for deep networks. In International conference on machine learning, pages 3319–3328. PMLR, 2017.
  55. A rigorous study of integrated gradients method and extensions to internal neuron attributions. In International Conference on Machine Learning, pages 14485–14508. PMLR, 2022.
  56. Visualizing the impact of feature attribution baselines. Distill, 2020. https://distill.pub/2020/attribution-baselines.
  57. Revisiting the evaluation of class activation mapping for explainability: A novel metric and experimental analysis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2299–2304, 2021.
  58. medxgan: Visual explanations for medical classifiers through a generative latent space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 2936–2945, June 2022.
  59. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR, 2018.
  60. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34:8780–8794, 2021.
  61. Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015 Conference Proceedings, 2022.
  62. Denoising diffusion implicit models. In International Conference on Learning Representations, 2021.
  63. Pei-bai Zhou. Finite difference method. Numerical Analysis of Electromagnetic Fields, 1993.
  64. Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV), December 2015.
  65. Progressive growing of gans for improved quality, stability, and variation. In International Conference on Learning Representations, 2017.
  66. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708, 2017.
  67. Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 590–597, 2019.
  68. Be careful when evaluating explanations regarding ground truth. arXiv preprint arXiv:2311.04813, 2023.
  69. A style-based generator architecture for generative adversarial networks. In IEEE Transactions on Pattern Analysis &; Machine Intelligence, 2021.
Citations (1)
View on Semantic Scholar

Summary

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

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

YouTube