美文网首页
XGAN: UNSUPERVISED IMAGE-TO-IMAG

XGAN: UNSUPERVISED IMAGE-TO-IMAG

作者: klory | 来源:发表于2018-01-26 05:20 被阅读113次

    https://arxiv.org/pdf/1711.05139.pdf

    Novelty

    • Unsupervise
    • Two domain share the same latent space
    • predict class at encoder

    Problem

    • Only two domains at a time, need to train new model for new domain

    Structure

    Structure.png

    Loss

    Loss.png

    Dataset

    Self-created CartoonSet dataset

    相关文章

      网友评论

          本文标题:XGAN: UNSUPERVISED IMAGE-TO-IMAG

          本文链接:https://www.haomeiwen.com/subject/vgqiaxtx.html