资源分类
》 资源 》论文》Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

2020-03-16 | |  57 |   54 |   0

Abstract

Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data. CycleGAN was recently proposed for this problem, but critically assumes the underlying inter-domain mapping is approximately deterministic and one-to-one. This assumption renders the model ineffective for tasks requiring flexible, many-to-many mappings. We propose a new model, called Augmented CycleGAN, which learns many-to-many mappings between domains. We examine Augmented CycleGAN qualitatively and quantitatively on several image datasets.

上一篇：Thompson Sampling for Combinatorial Semi-Bandits

下一篇：A Distributed Second-Order Algorithm You Can Trust

用户评价
全部评价

热门资源

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Rating-Boosted La...

    The performance of a recommendation system reli...

  • Hierarchical Task...

    We extend hierarchical task network planning wi...