Discovering interpretable latent space directions of gans beyond binary attributes
Generative adversarial networks (GANs) learn to map noise latent vectors to high- fidelity image outputs. It is found that the input latent space shows semantic correlations with the output image space. Recent works aim to interpret the latent space and discover meaningful directions that correspond...
Saved in:
Main Authors: | YANG, Huiting, CHAI, Liangyu, WEN, Qiang, ZHAO, Shuang, SUN, Zixun, HE, Shengfeng |
---|---|
格式: | text |
語言: | English |
出版: |
Institutional Knowledge at Singapore Management University
2021
|
主題: | |
在線閱讀: | https://ink.library.smu.edu.sg/sis_research/8521 https://ink.library.smu.edu.sg/context/sis_research/article/9524/viewcontent/Discovering_Interpretable_Latent_Space_Directions_of_GANs_Beyond_Binary_Attributes.pdf |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Attribute-assisted reranking for web image retrieval
由: Cai, J., et al.
出版: (2013) -
Spoken attributes: Mixing binary and relative attributes to say the right thing
由: Sadovnik A., et al.
出版: (2018) -
Visual query attributes suggestion
由: Bian, J., et al.
出版: (2013) -
Attribute-restricted latent topic model for person re-identification
由: Liu, X., et al.
出版: (2014) -
It's not polite to point: Describing people with uncertain attributes
由: Sadovnik A., et al.
出版: (2018)