LIA: Latently Invertible Autoencoder with Adversarial Learning

By Jiapeng Zhu, Deli Zhao, Bo Zhang. 2019

21 citations recorded by the source corpus.

Subfields: Generative Models, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

1. Yujun Shen
2. Bolei Zhou
3. Daniel Cohen-Or
4. Jiapeng Zhu
5. Eli Shechtman
6. Yinghao Xu
7. Ceyuan Yang
8. Xiaoou Tang

In Representation & Self-Supervised Learning

1. Yujun Shen
2. Bolei Zhou
3. Xiaoou Tang
4. Ceyuan Yang
5. Jiapeng Zhu
6. Yinghao Xu
7. Deli Zhao
8. Antonio Torralba

Citations in the corpus

• D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation (2021, neutral): “However, these methods have some trouble manipulating real images because of imperfect reconstruction [107, 7].”
• Interpreting the Latent Space of GANs for Semantic Face Editing (2019, methodology): “To make GANs applicable for real image processing, existing methods proposed to reverse the mapping from the latent space to the image space [27, 39, 24, 5, 16] or learn an additional encoder associated with the GAN training [13, 12, 38].”
• Generative Hierarchical Features from Synthesizing Images (2020, background): “1, unlike prior work [37, 54, 55, 41, 45] that treats theW space as the representation space, we are the first to use the style codes y instead.”
• InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs (2020, methodology): “In Figure 14, we use LIA [51] as the generative model, which learns an additional encoder beyond the original two-player game in GANs.”
• In-Domain GAN Inversion for Real Image Editing (2020, methodology): “As a result, the disentangled space W is widely used for the GAN inversion task [29,35,1,20].”