Abstract
Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training set, frequently caused by the co-occurrence of relevant features and irrelevant ones. To mitigate this issue, we require learning algorithms that prevent the propagation of known bias from the dataset into the classifier. We present a novel adversarial debiasing method, which addresses a feature of which we know that it is spuriously connected to the labels of training images but statistically independent of the labels for test images. The debiasing stops the classifier from falsly identifying this irrelevant feature as important. Irrelevant features co-occur with important features in a wide range of bias-related problems for many computer vision tasks, such as automatic skin cancer detection or driver assistance. We argue by a mathematical proof that our approach is superior to existing techniques for the abovementioned bias. Our experiments show that our approach performs better than the state-of-the-art on a well-known benchmark dataset with real-world images of cats and dogs.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Adeli, E., et al.: Representation learning with statistical independence to mitigate bias. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2513–2523 (2021)
Ali Shah, S.A., Uddin, I., Aziz, F., Ahmad, S., Al-Khasawneh, M.A., Sharaf, M.: An enhanced deep neural network for predicting workplace absenteeism. Complexity 2020, 1–12 (2020)
Alvi, M., Zisserman, A., Nellåker, C.: Turning a blind eye: explicit removal of biases and variation from deep neural network embeddings. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11129, pp. 556–572. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11009-3_34
Angwin, J., Larson, J., Mattu, S., Kirchner, L.: Machine Bias. PropPblica (2016). https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
Bandi, P., et al.: From detection of individual metastases to classification of lymph node status at the patient level: the camelyon17 challenge. IEEE Trans. Med. Imaging 38(2), 550–560 (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Fukumizu, K., Gretton, A., Sun, X., Schölkopf, B.: Kernel measures of conditional dependence. In: Advances in Neural Information Processing Systems, pp. 489–496 (2008)
Gretton, A., Fukumizu, K., Teo, C.H., Song, L., Schölkopf, B., Smola, A.J.: A kernel statistical test of independence. In: Advances in Neural Information Processing Systems, pp. 585–592 (2008)
Hartmann, B., Raste, T., Kretschmann, M., Amthor, M., Schneider, F., Denzler, J.: Aquaplaning - a potential hazard also for automated driving. In: ITS Automotive Nord e.V. (Hrsg.) Braunschweig (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Kim, B., Kim, H., Kim, K., Kim, S., Kim, J.: Learning not to learn: training deep neural networks with biased data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9012–9020 (2019)
Lakkaraju, H., Kamar, E., Caruana, R., Horvitz, E.: Discovering blind spots of predictive models: representations and policies for guided exploration. arXiv preprint arXiv:1610.09064 (2016)
Muckatira, S.: Properties of winning tickets on skin lesion classification. arXiv preprint arXiv:2008.12141 (2020)
Pearl, J.: Causality. Cambridge University Press, Cambridge (2009)
Perez, F., Vasconcelos, C., Avila, S., Valle, E.: Data augmentation for skin lesion analysis. In: Stoyanov, D., et al. (eds.) CARE/CLIP/OR 2.0/ISIC -2018. LNCS, vol. 11041, pp. 303–311. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01201-4_33
Reimers, C., Requena-Mesa, C.: Deep learning-an opportunity and a challenge for geo-and astrophysics. In: Knowledge Discovery in Big Data from Astronomy and Earth Observation, pp. 251–265. Elsevier (2020)
Reimers, C., Runge, J., Denzler, J.: Determining the relevance of features for deep neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 330–346. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58574-7_20
Sarmanov, O.V.: The maximum correlation coefficient (symmetrical case). In: Doklady Akademii Nauk, vol. 120, pp. 715–718. Russian Academy of Sciences (1958)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR 2011, pp. 1521–1528. IEEE (2011)
Tschandl, P., et al.: Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study. Lancet Oncol. 20(7), 938–947 (2019)
Tschandl, P., Rosendahl, C., Kittler, H.: The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. data 5, 180161 (2018)
Wang, A., Narayanan, A., Russakovsky, O.: REVISE: a tool for measuring and mitigating bias in visual datasets. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 733–751. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_43
Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pp. 335–340 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Reimers, C., Bodesheim, P., Runge, J., Denzler, J. (2021). Conditional Adversarial Debiasing: Towards Learning Unbiased Classifiers from Biased Data. In: Bauckhage, C., Gall, J., Schwing, A. (eds) Pattern Recognition. DAGM GCPR 2021. Lecture Notes in Computer Science(), vol 13024. Springer, Cham. https://doi.org/10.1007/978-3-030-92659-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-92659-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92658-8
Online ISBN: 978-3-030-92659-5
eBook Packages: Computer ScienceComputer Science (R0)