2020

Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency

Lu, Guansong, Zhou, Zhiming, Shen, Jian et al.

Understand

Recent advances in large-scale optimal transport have greatly extended its application scenarios in machine learning.

However, existing methods either not explicitly learn the transport map or do not support general cost function.
In this paper, we propose an end-to-end approach for large-scale optimal transport, which directly solves the transport map and is compatible with general cost function.
It models the transport map via stochastic neural networks and enforces the constraint on the marginal distributions via adversarial training.

Built on

Kantorovich, L.V.: On the translocation of masses. In: Dokl. Akad. Nauk. USSR (NS). vol. 37, pp. 199–201 (1942)
1942
Earlier work this paper cites.
Denker, J.S., Gardner, W., Graf, H.P., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D., Baird, H.S., Guyon, I.: Neural network recognizer for hand-written zip code digits. In: NIPS. pp. 323–331 (1989)
1989
Earlier work this paper cites.
Brenier, Y.: Polar factorization and monotone rearrangement of vector-valued functions. Communications on pure and applied mathematics 44
1991
Earlier work this paper cites.
Damian, K., Comm, B., Garret, M.: The minimum Cost Flow Problem and The Network Simplex Method. Ph.D. thesis, Dissertation de Mastère, Université College Gublin, Irlande (1991)
1991
Earlier work this paper cites.
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86
1998
Earlier work this paper cites.
Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. IJCV 40
2000
Earlier work this paper cites.
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. science 313
2006
Earlier work this paper cites.
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
2011
Earlier work this paper cites.
Cuturi, M.: Sinkhorn distances: Lightspeed computation of optimal transport. In: NIPS. pp. 2292–2300 (2013)
2013
Earlier work this paper cites.
Ferradans, S., Papadakis, N., Peyré, G., Aujol, J.F.: Regularized discrete optimal transport. SIAM Journal on Imaging Sciences 7
2014
Earlier work this paper cites.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: NIPS (2014)
2014
Earlier work this paper cites.
Yu, A., Grauman, K.: Fine-grained visual comparisons with local learning. In: CVPR. pp. 192–199 (2014)
2014
Earlier work this paper cites.
Santambrogio, F.: Optimal transport for applied mathematicians. Birkäuser, NY 55
2015
Earlier work this paper cites.

Similar

Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. The Journal of Machine Learning Research 17
2016
Cited alongside, same era.
Genevay, A., Cuturi, M., Peyré, G., Bach, F.: Stochastic optimization for large-scale optimal transport. In: NIPS. pp. 3440–3448 (2016)
2016
Cited alongside, same era.
He, D., Xia, Y., Qin, T., Wang, L., Yu, N., Liu, T., Ma, W.Y.: Dual learning for machine translation. In: NIPS. pp. 820–828 (2016)
2016
Cited alongside, same era.
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR. pp. 770–778 (2016)
2016
Cited alongside, same era.
Liu, M.Y., Tuzel, O.: Coupled generative adversarial networks. In: NIPS. pp. 469–477 (2016)
2016
Cited alongside, same era.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR. pp. 2818–2826 (2016)
2016
Cited alongside, same era.
Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)
Original
2016
Cited alongside, same era.
Zhu, J.Y., Krähenbühl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: ECCV. pp. 597–613. Springer (2016)
2016
Cited alongside, same era.
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein gan. arXiv preprint arXiv:1701.07875 (2017)
Original
2017
Cited alongside, same era.
Courty, N., Flamary, R., Habrard, A., Rakotomamonjy, A.: Joint distribution optimal transportation for domain adaptation. In: NIPS. pp. 3730–3739 (2017)
2017
Cited alongside, same era.
Courty, N., Flamary, R., Tuia, D., Rakotomamonjy, A.: Optimal transport for domain adaptation. PAMI 39
2017
Cited alongside, same era.
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein gans. arXiv preprint arXiv:1704.00028 (2017)
Original
2017
Cited alongside, same era.

Then

Kim, T., Cha, M., Kim, H., Lee, J.K., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. arXiv preprint arXiv:1703.05192 (2017)
Original
2017
Later among the works it cites.
Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: NIPS. pp. 700–708 (2017)
2017
Later among the works it cites.
Seguy, V., Damodaran, B.B., Flamary, R., Courty, N., Rolet, A., Blondel, M.: Large-scale optimal transport and mapping estimation. arXiv preprint arXiv:1711.02283 (2017)
Original
2017
Later among the works it cites.
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR. pp. 7167–7176 (2017)
2017
Later among the works it cites.
Yi, Z., Zhang, H.R., Tan, P., Gong, M.: Dualgan: Unsupervised dual learning for image-to-image translation. In: ICCV. pp. 2868–2876 (2017)
2017
Later among the works it cites.
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint (2017)
2017
Later among the works it cites.
Bińkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans. arXiv preprint arXiv:1801.01401 (2018)
Original
2018
Later among the works it cites.
Damodaran, B.B., Kellenberger, B., Flamary, R., Tuia, D., Courty, N.: Deepjdot: Deep joint distribution optimal transport for unsupervised domain adaptation. In: ECCV. pp. 467–483. Springer (2018)
2018
Later among the works it cites.
Yang, K.D., Uhler, C.: Scalable unbalanced optimal transport using generative adversarial networks. arXiv preprint arXiv:1810.11447 (2018)
Original
2018
Later among the works it cites.
Leygonie, J., She, J., Almahairi, A., Rajeswar, S., Courville, A.: Adversarial computation of optimal transport maps. arXiv preprint arXiv:1906.09691 (2019)
Original
2019
Later among the works it cites.
Lu, G., Zhou, Z., Song, Y., Ren, K., Yu, Y.: Guiding the one-to-one mapping in cyclegan via optimal transport. In: AAAI. vol. 33, pp. 4432–4439 (2019)
2019
Later among the works it cites.
Makkuva, A.V., Taghvaei, A., Oh, S., Lee, J.D.: Optimal transport mapping via input convex neural networks. arXiv preprint arXiv:1908.10962 (2019)
Original
2019
Later among the works it cites.
Xie, Y., Chen, M., Jiang, H., Zhao, T., Zha, H.: On scalable and efficient computation of large scale optimal transport. arXiv preprint arXiv:1905.00158 (2019)
Original
2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…