Abstract
Existing generative adversarial networks (GANs) focus on generating realistic images based on CNN-derived image features, but fail to preserve the structural properties of real images. This can be fatal in applications where the underlying structure (e.g.., neurons, vessels, membranes, and road networks) of the image carries crucial semantic meaning. In this paper, we propose a novel GAN model that learns the topology of real images, i.e., connectedness and loopy-ness. In particular, we introduce a new loss that bridges the gap between synthetic image distribution and real image distribution in the topological feature space. By optimizing this loss, the generator produces images with the same structural topology as real images. We also propose new GAN evaluation metrics that measure the topological realism of the synthetic images. We show in experiments that our method generates synthetic images with realistic topology. We also highlight the increased performance that our method brings to downstream tasks such as segmentation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The persistence diagram definition does not require the input to be a distance transform. It can be an arbitrary scalar function defined on a topological space.
- 2.
There are more technical reasons for adding the diagonal line into the diagram, related to the stability of the metric. See [12].
References
Abbasi-Sureshjani, S., Smit-Ockeloen, I., Bekkers, E., Dashtbozorg, B., ter Haar Romeny, B.: Automatic detection of vascular bifurcations and crossings in retinal images using orientation scores. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), pp. 189–192, April 2016. https://doi.org/10.1109/ISBI.2016.7493241
Abbasi-Sureshjani, S., Smit-Ockeloen, I., Zhang, J., Ter Haar Romeny, B.: Biologically-inspired supervised vasculature segmentation in SLO retinal fundus images. In: Kamel, M., Campilho, A. (eds.) Image Analysis and Recognition, pp. 325–334. Springer International Publishing, Cham (2015)
Adams, H., et al.: Persistence images: a stable vector representation of persistent homology. J. Mach. Learn. Res. 18(1), 218–252 (2017)
Arganda-Carreras, I., et al.: Crowdsourcing the creation of image segmentation algorithms for connectomics. Front. Neuroanat. 9, 142 (2015). https://doi.org/10.3389/fnana.2015.00142. https://www.frontiersin.org/article/10.3389/fnana.2015.00142
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017)
Bonneel, N., Rabin, J., Peyré, G., Pfister, H.: Sliced and radon Wasserstein Barycenters of measures. J. Math. Imaging Vis. 51(1), 22–45 (2015)
Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (2018)
Brüel-Gabrielsson, R., Nelson, B.J., Dwaraknath, A., Skraba, P., Guibas, L.J., Carlsson, G.: A topology layer for machine learning. arXiv preprint arXiv:1905.12200 (2019)
Carriere, M., Cuturi, M., Oudot, S.: Sliced Wasserstein kernel for persistence diagrams. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 664–673. JMLR. org (2017)
Chen, C., Ni, X., Bai, Q., Wang, Y.: A topological regularizer for classifiers via persistent homology. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 2573–2582 (2019)
Clough, J.R., Oksuz, I., Byrne, N., Schnabel, J.A., King, A.P.: Explicit topological priors for deep-learning based image segmentation using persistent homology. In: Chung, A.C.S., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 16–28. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20351-1_2
Cohen-Steiner, D., Edelsbrunner, H., Harer, J.: Stability of persistence diagrams. Discrete Comput. Geom. 37(1), 103–120 (2007)
Cohen-Steiner, D., Edelsbrunner, H., Harer, J., Mileyko, Y.: Lipschitz functions have l p-stable persistence. Found. Comput. Math. 10(2), 127–139 (2010)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Miccai challenge on circuit reconstruction from electron microscopy images. https://cremi.org/
Edelsbrunner, H., Harer, J.: Computational Topology: An Introduction. American Mathematical Society, Providence (2010)
Fabbri, R., Costa, L.D.F., Torelli, J.C., Bruno, O.M.: 2D Euclidean distance transform algorithms: a comparative survey. ACM Comput. Surv. (CSUR) 40(1), 1–44 (2008)
Fu, H., Gong, M., Wang, C., Batmanghelich, K., Zhang, K., Tao, D.: Geometry-consistent generative adversarial networks for one-sided unsupervised domain mapping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2427–2436 (2019)
Ghafoorian, M., Nugteren, C., Baka, N., Booij, O., Hofmann, M.: EL-GAN: embedding loss driven generative adversarial networks for lane detection. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11129, pp. 256–272. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11009-3_15
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Gretton, A., Borgwardt, K., Rasch, M., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13, 723–773 (2012)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)
He, Y., et al.: Fully convolutional boundary regression for retina OCT segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11764, pp. 120–128. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32239-7_14
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Guyon, I., et al., (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 6626–6637. Curran Associates, Inc. (2017). http://papers.nips.cc/paper/7240-gans-trained-by-a-two-time-scale-update-rule-converge-to-a-local-nash-equilibrium.pdf
Hofer, C., Kwitt, R., Niethammer, M., Dixit, M.: Connectivity-optimized representation learning via persistent homology. In: International Conference on Machine Learning, pp. 2751–2760 (2019)
Hofer, C., Kwitt, R., Niethammer, M., Uhl, A.: Deep learning with topological signatures. In: Advances in Neural Information Processing Systems, pp. 1634–1644 (2017)
Hoover, A.D., Kouznetsova, V., Goldbaum, M.: Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imaging 19(3), 203–210 (2000). https://doi.org/10.1109/42.845178
Hu, X., Li, F., Samaras, D., Chen, C.: Topology-preserving deep image segmentation. In: Advances in Neural Information Processing Systems, pp. 5658–5669 (2019)
Hwang, J.J., Ke, T.W., Shi, J., Yu, S.X.: Adversarial structure matching for structured prediction tasks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4056–4065 (2019)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)
Khrulkov, V., Oseledets, I.: Geometry score: a method for comparing generative adversarial networks. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 2621–2629. PMLR, Stockholmsmässan, Stockholm Sweden, 10–15 July 2018
Kossaifi, J., Tran, L., Panagakis, Y., Pantic, M.: GAGAN: geometry-aware generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 878–887 (2018)
Kusano, G., Hiraoka, Y., Fukumizu, K.: Persistence weighted Gaussian kernel for topological data analysis. In: International Conference on Machine Learning, pp. 2004–2013 (2016)
Li, C.L., Chang, W.C., Cheng, Y., Yang, Y., Póczos, B.: MMD GAN: towards deeper understanding of moment matching network. In: Advances in Neural Information Processing Systems, pp. 2203–2213 (2017)
Lim, J.H., Ye, J.C.: Geometric GAN. arXiv preprint arXiv:1705.02894 (2017)
Liu, H., Gu, X., Samaras, D.: Wasserstein GAN with quadratic transport cost. In: The IEEE International Conference on Computer Vision (ICCV), October 2019
Liu, H., Xianfeng, G., Samaras, D.: A two-step computation of the exact GAN Wasserstein distance. In: International Conference on Machine Learning, pp. 3165–3174 (2018)
Liu, S., Bousquet, O., Chaudhuri, K.: Approximation and convergence properties of generative adversarial learning. In: Advances in Neural Information Processing Systems, pp. 5545–5553 (2017)
Luc, P., Couprie, C., Chintala, S., Verbeek, J.: Semantic segmentation using adversarial networks. arXiv preprint arXiv:1611.08408 (2016)
Mescheder, L., Nowozin, S., Geiger, A.: Which training methods for GANs do actually converge? In: International Conference on Machine Learning (2018)
Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: International Conference on Machine Learning (2018)
Mosinska, A., Márquez-Neila, P., Koziński, M., Fua, P.: Beyond the pixel-wise loss for topology-aware delineation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Mroueh, Y., Sercu, T.: Fisher GAN. In: Advances in Neural Information Processing Systems, pp. 2513–2523 (2017)
Mroueh, Y., Sercu, T., Goel, V.: McGan: mean and covariance feature matching GAN. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 2527–2535. PMLR, International Convention Centre, Sydney, Australia, 06–11 August 2017
Munkres, J.R.: Elements of Algebraic Topology. CRC Press, Boca Raton (2018)
Ni, X., Quadrianto, N., Wang, Y., Chen, C.: Composing tree graphical models with persistent homology features for clustering mixed-type data. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2622–2631. JMLR. org (2017)
Nowozin, S., Cseke, B., Tomioka, R.: F-GAN: training generative neural samplers using variational divergence minimization. In: Advances in Neural Information Processing Systems, pp. 271–279 (2016)
Owen, C.G., et al.: Measuring retinal vessel tortuosity in 10-year-old children: validation of the computer-assisted image analysis of the retina (CAIAR) program. Invest. Ophthalmol. Vis. Sci. 50(5), 2004–2010 (2009). https://doi.org/10.1167/iovs.08-3018
Peyré, G., Cuturi, M.: Computational optimal transport foundations and trends. Mach. Learn. 11(2019), 355 (1803)
Qi, G.J., Zhang, L., Hu, H., Edraki, M., Wang, J., Hua, X.S.: Global versus localized generative adversarial nets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1517–1525 (2018)
Qin, Y., et al.: AirwayNet: a voxel-connectivity aware approach for accurate airway segmentation using convolutional neural networks. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 212–220. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_24
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Ramamurthy, K.N., Varshney, K., Mody, K.: Topological data analysis of decision boundaries with application to model selection. In: International Conference on Machine Learning, pp. 5351–5360 (2019)
Reininghaus, J., Huber, S., Bauer, U., Kwitt, R.: A stable multi-scale kernel for topological machine learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4741–4748 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, pp. 2234–2242 (2016)
Shaham, T.R., Dekel, T., Michaeli, T.: Singan: learning a generative model from a single natural image. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4570–4580 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)
Staal, J., Abràmoff, M.D., Niemeijer, M., Viergever, M.A., Van Ginneken, B.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23(4), 501–509 (2004)
Thanh-Tung, H., Tran, T., Venkatesh, S.: Improving generalization and stability of generative adversarial networks. In: International Conference on Learning Representations (2019)
Tyleček, R., Šára, R.: Spatial pattern templates for recognition of objects with regular structure. In: Weickert, J., Hein, M., Schiele, B. (eds.) GCPR 2013. LNCS, vol. 8142, pp. 364–374. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40602-7_39
Villani, C.: Optimal Transport: Old and New, vol. 338. Springer Science & Business Media, Berlin Heidelberg (2008). https://doi.org/10.1007/978-3-540-71050-9
Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8798–8807 (2018)
Wu, P., et al.: Optimal topological cycles and their application in cardiac trabeculae restoration. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 80–92. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59050-9_7
Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning, pp. 7354–7363 (2019)
Zhao, Q., Wang, Y.: Learning metrics for persistence-based summaries and applications for graph classification. In: Advances in Neural Information Processing Systems, pp. 9859–9870 (2019)
Zhao, Q., Ye, Z., Chen, C., Wang, Y.: Persistence enhanced graph neural network. In: International Conference on Artificial Intelligence and Statistics, pp. 2896–2906 (2020)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)
Acknowledgement
Fan Wang and Chao Chen’s research was partially supported by NSF IIS-1855759, CCF-1855760 and IIS-1909038. Huidong Liu and Dimitris Samaras were partially supported from the Partner University Fund, the SUNY2020 Infrastructure Transportation Security Center, and a gift from Adobe.
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
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, F., Liu, H., Samaras, D., Chen, C. (2020). TopoGAN: A Topology-Aware Generative Adversarial Network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12348. Springer, Cham. https://doi.org/10.1007/978-3-030-58580-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-58580-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58579-2
Online ISBN: 978-3-030-58580-8
eBook Packages: Computer ScienceComputer Science (R0)