Abstract
Learning disentangled representations requires either supervision or the introduction of specific model designs and learning constraints as biases. InfoGAN is a popular disentanglement framework that learns unsupervised disentangled representations by maximising the mutual information between latent representations and their corresponding generated images. Maximisation of mutual information is achieved by introducing an auxiliary network and training with a latent regression loss. In this short exploratory paper, we study the use of the Hilbert-Schmidt Independence Criterion (HSIC) to approximate mutual information between latent representation and image, termed HSIC-InfoGAN. Directly optimising the HSIC loss avoids the need for an additional auxiliary network. We qualitatively compare the level of disentanglement in each model, suggest a strategy to tune the hyperparameters of HSIC-InfoGAN, and discuss the potential of HSIC-InfoGAN for medical applications.
Keywords
- Disentangled representation learning
- HSIC
- InfoGAN
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Belghazi, M.I., et al.: Mutual information neural estimation. In: International Conference on Machine Learning, pp. 531–540. PMLR (2018)
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)
Chaitanya, K., Erdil, E., Karani, N., Konukoglu, E.: Contrastive learning of global and local features for medical image segmentation with limited annotations. Adv. Neural. Inf. Process. Syst. 33, 12546–12558 (2020)
Chartsias, A., Joyce, T., et al.: Disentangled representation learning in cardiac image analysis. Media 58, 101535 (2019)
Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley Interscience (2006)
Du, Y., Li, S., Sharma, Y., Tenenbaum, J., Mordatch, I.: Unsupervised learning of compositional energy concepts. Adv. Neural. Inf. Process. Syst. 34, 15608–15620 (2021)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Huang, X., Liu, M.Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision, pp. 172–189 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Proceedings of the International Conference on Learning Representations (2013)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Liu, X., Sanchez, P., Thermos, S., O’Neil, A.Q., Tsaftaris, S.A.: Learning disentangled representations in the imaging domain. Med. Image Anal. 102516 (2022)
Liu, X., Thermos, S., Chartsias, A., O’Neil, A., Tsaftaris, S.A.: Disentangled representations for domain-generalized cardiac segmentation. In: Puyol Anton, E., et al. (eds.) STACOM 2020. LNCS, vol. 12592, pp. 187–195. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68107-4_19
Liu, X., Thermos, S., O’Neil, A., Tsaftaris, S.A.: Semi-supervised meta-learning with disentanglement for domain-generalised medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 307–317. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87196-3_29
Liu, X., Thermos, S., Valvano, G., Chartsias, A., O’Neil, A., Tsaftaris, S.A.: Metrics for exposing the biases of content-style disentanglement. In: British Machine Vision Conference (2021)
Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations. In: ICML, pp. 4114–4124. PMLR (2019)
Ma, W.D.K., Lewis, J., Kleijn, W.B.: The HSIC bottleneck: deep learning without back-propagation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5085–5092 (2020)
Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: International Conference on Machine Learning, pp. 2642–2651. PMLR (2017)
Papamakarios, G., Nalisnick, E.T., Rezende, D.J., Mohamed, S., Lakshminarayanan, B.: Normalizing flows for probabilistic modeling and inference. J. Mach. Learn. Res. 22(57), 1–64 (2021)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Sanchez, P., Tsaftaris, S.A.: Diffusion causal models for counterfactual estimation. In: First Conference on Causal Learning and Reasoning (2021)
Thermos, S., Liu, X., O’Neil, A., Tsaftaris, S.A.: Controllable cardiac synthesis via disentangled anatomy arithmetic. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 160–170. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87199-4_15
Yang, J., Dvornek, N.C., Zhang, F., Chapiro, J., Lin, M.D., Duncan, J.S.: Unsupervised domain adaptation via disentangled representations: application to cross-modality liver segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 255–263. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_29
Zhu, J.Y., et al.: Toward multimodal image-to-image translation. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Acknowledgement
This work was supported by the University of Edinburgh, the Royal Academy of Engineering and Canon Medical Research Europe by a PhD studentship to Xiao Liu. This work was partially supported by the Alan Turing Institute under the EPSRC grant EP/N510129/1. S.A. Tsaftaris acknowledges the support of Canon Medical and the Royal Academy of Engineering and the Research Chairs and Senior Research Fellowships scheme (grant RCSRF1819\(\backslash 8\backslash 25\)).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, X., Thermos, S., Sanchez, P., O’Neil, A.Q., Tsaftaris, S.A. (2023). HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual Information. In: Fragemann, J., Li, J., Liu, X., Tsaftaris, S.A., Egger, J., Kleesiek, J. (eds) Medical Applications with Disentanglements. MAD 2022. Lecture Notes in Computer Science, vol 13823. Springer, Cham. https://doi.org/10.1007/978-3-031-25046-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-25046-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25045-3
Online ISBN: 978-3-031-25046-0
eBook Packages: Computer ScienceComputer Science (R0)
-
Published in cooperation with
http://miccai.org/
