Spectral normalization and relativistic adversarial training for conditional pose generation with self-attention

Yusuke Horiuchi, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We address the problem of conditional image generation of synthesizing a new image of an individual given a reference image and target pose. We base our approach on generative adversarial networks and leverage deformable skip connections to deal with pixel-to-pixel misalignments, self-attention to leverage complementary features in separate portions of the image, e.g., arms or legs, and spectral normalization to improve the quality of the synthesized images. We train the synthesis model with a nearest-neighbour loss in combination with a relativistic average hinge adversarial loss. We evaluate on the Market-1501 dataset and show how our proposed approach can surpass existing approaches in conditional image synthesis performance.

Original languageEnglish
Title of host publicationProceedings of the 16th International Conference on Machine Vision Applications, MVA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9784901122184
DOIs
Publication statusPublished - 2019 May
Event16th International Conference on Machine Vision Applications, MVA 2019 - Tokyo, Japan
Duration: 2019 May 272019 May 31

Publication series

NameProceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

Conference

Conference16th International Conference on Machine Vision Applications, MVA 2019
CountryJapan
CityTokyo
Period19/5/2719/5/31

ASJC Scopus subject areas

  • Computer Science Applications
  • Signal Processing
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Spectral normalization and relativistic adversarial training for conditional pose generation with self-attention'. Together they form a unique fingerprint.

  • Cite this

    Horiuchi, Y., Iizuka, S., Simo-Serra, E., & Ishikawa, H. (2019). Spectral normalization and relativistic adversarial training for conditional pose generation with self-attention. In Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019 [8758013] (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/MVA.2019.8758013