Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency
arXiv:2003.06635
Abstract
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. The proposed framework can be further extended towards learning Monge map or optimal bijection via adopting cycle-consistency constraint(s). We verify the effectiveness of the proposed method and demonstrate its superior performance against existing methods with large-scale real-world applications, including domain adaptation, image-to-image translation, and color transfer.
References in corpus (11)
- Wide Residual Networks
- Improved Training of Wasserstein GANs
- CyCADA: Cycle-Consistent Adversarial Domain Adaptation
- Dual Learning for Machine Translation
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
- Demystifying MMD GANs
- Large-Scale Optimal Transport and Mapping Estimation
- Optimal transport mapping via input convex neural networks
- Adversarial Computation of Optimal Transport Maps
- Scalable Unbalanced Optimal Transport using Generative Adversarial Networks
- On Scalable and Efficient Computation of Large Scale Optimal Transport