Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DeCoDEx: Confounder Detector Guidance for Improved Diffusion-based Counterfactual Explanations (2405.09288v1)

Published 15 May 2024 in cs.CV

Abstract: Deep learning classifiers are prone to latching onto dominant confounders present in a dataset rather than on the causal markers associated with the target class, leading to poor generalization and biased predictions. Although explainability via counterfactual image generation has been successful at exposing the problem, bias mitigation strategies that permit accurate explainability in the presence of dominant and diverse artifacts remain unsolved. In this work, we propose the DeCoDEx framework and show how an external, pre-trained binary artifact detector can be leveraged during inference to guide a diffusion-based counterfactual image generator towards accurate explainability. Experiments on the CheXpert dataset, using both synthetic artifacts and real visual artifacts (support devices), show that the proposed method successfully synthesizes the counterfactual images that change the causal pathology markers associated with Pleural Effusion while preserving or ignoring the visual artifacts. Augmentation of ERM and Group-DRO classifiers with the DeCoDEx generated images substantially improves the results across underrepresented groups that are out of distribution for each class. The code is made publicly available at https://github.com/NimaFathi/DeCoDEx.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (24)
  1. Gifsplanation via latent shift: a simple autoencoder approach to counterfactual generation for chest x-rays. In Medical Imaging with Deep Learning, pages 74–104. PMLR, 2021.
  2. Ai for radiographic covid-19 detection selects shortcuts over signal. Nature Machine Intelligence, 3(7):610–619, 2021.
  3. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34:8780–8794, 2021.
  4. Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231, 2018.
  5. Shortcut learning in deep neural networks. Nature Machine Intelligence, 2(11):665–673, 2020.
  6. Denoising diffusion probabilistic models. In Advances in Neural Information Processing Systems, volume 33, pages 6840–6851, 2020.
  7. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708, 2017.
  8. Deep transfer learning to quantify pleural effusion severity in chest x-rays. BMC Medical Imaging, 22(1):1–11, 2022.
  9. 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.
  10. Diffusion models for counterfactual explanations. In Proceedings of the Asian Conference on Computer Vision, pages 858–876, 2022.
  11. Adversarial examples for evaluating reading comprehension systems. arXiv preprint arXiv:1707.07328, 2017.
  12. Diffusion models for medical image analysis: A comprehensive survey. arXiv preprint arXiv:2211.07804, 2022.
  13. Debiasing counterfactuals in the presence of spurious correlations. In Workshop on Clinical Image-Based Procedures, pages 276–286. Springer, 2023.
  14. Richard W Light. Pleural effusion. New England Journal of Medicine, 346(25):1971–1977, 2002.
  15. Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 conference on fairness, accountability, and transparency, pages 607–617, 2020.
  16. Countergan: Generating realistic counterfactuals with residual generative adversarial nets. arXiv preprint arXiv:2009.05199, 2020.
  17. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization, 2020.
  18. Fairness by learning orthogonal disentangled representations. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIX 16, pages 746–761. Springer, 2020.
  19. Right for the wrong reason: Can interpretable ml techniques detect spurious correlations? In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 425–434. Springer, 2023a.
  20. Inherently interpretable multi-label classification using class-specific counterfactuals. arXiv preprint arXiv:2303.00500, 2023b.
  21. Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2097–2106, 2017.
  22. Towards fairness in visual recognition: Effective strategies for bias mitigation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8919–8928, 2020.
  23. Diffusion-gan: Training gans with diffusion. arXiv preprint arXiv:2206.02262, 2022.
  24. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS medicine, 15(11):e1002683, 2018.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Nima Fathi (11 papers)
  2. Amar Kumar (12 papers)
  3. Brennan Nichyporuk (17 papers)
  4. Mohammad Havaei (31 papers)
  5. Tal Arbel (41 papers)

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