paper-with-me

홈 › Papers

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

2020-03-14 · Guansong Lu, Zhiming Zhou, Jian Shen, Cheng Chen, Wei-Nan Zhang, Yong Yu

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.

📄 PDF Abstract BibTeX arXiv:2003.06635

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationImage-to-Image TranslationTranslation

Similar Papers 제목 키워드 기반

Noise-Guided Transport for Imitation Learning

2025-09-30 · Lionel Blondé, Joao A. Candido Ramos, Alexandros Kalousis arxiv

We consider imitation learning in the low-data regime, where only a limited number of expert demonstrations are available. In this setting, methods that rely on large-scale pretraining or high-capacity architectures can …

Continuous Control

Adversarial Risk via Optimal Transport and Optimal Couplings

2019-12-05 · ICML 2020 1 · Muni Sreenivas Pydi, Varun Jog

Modern machine learning algorithms perform poorly on adversarially manipulated data. Adversarial risk quantifies the error of classifiers in adversarial settings; adversarial classifiers minimize adversarial risk. In thi…

Binary Classification

OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack

2024-08-01 · Kuo Gai, Sicong Wang, Shihua Zhang

Deep neural networks (DNNs) are vulnerable to small adversarial perturbations of the inputs, posing a significant challenge to their reliability and robustness. Empirical methods such as adversarial training can defend a…

Adversarial AttackAdversarial Defense

Cycle monotonicity of adversarial attacks for optimal domain adaptation

2021-09-29 · Arip Asadulaev, Vitaly Shutov, Alexander Korotin, Alexander Panfilov 외

We reveal an intriguing connection between adversarial attacks and cycle monotone maps, also known as optimal transport maps. Based on this finding, we developed a novel method named source fiction for semi-supervised op…

Domain AdaptationSemi-supervised Domain Adaptation

Adversarial Computation of Optimal Transport Maps

2019-06-24 · Jacob Leygonie, Jennifer She, Amjad Almahairi, Sai Rajeswar 외

Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport (OT). Generative adversarial networks (GANs) are powerful generative models which have …