[ALAE] Adversarial Latent Autoencoders (Apr 2020 CVPR) - Githubissues

andrewjong / Deep-Learning-Paper-Surveys

Personal repository to track my paper reading

4 stars 1 forks source link

[ALAE] Adversarial Latent Autoencoders (Apr 2020 CVPR) #13

Open andrewjong opened 4 years ago

andrewjong commented 4 years ago

0. Article Information and Links

Paper link: https://github.com/podgorskiy/ALAE
Release date: YYYY/MM/DD
Number of citations (as of 2020/MM/DD):
Implementation code:
Supplemental links (e.g. results):
Publication: Conference YYYY

1. What do the authors try to accomplish?

2. What's great compared to previous research?

First autoencoder approach that jointly tackles GENERATIVE POWER and DISENTANGLED REPRESENTATIONS.

Unique

3. Where are the key elements of the technology and method?

4. How did you verify that it works?

5. Things to discuss? (e.g. weaknesses, potential for future work, relation to other work)

6. Are there any papers to read next?

7. References

andrewjong commented 4 years ago

Paused reading because doesn't seem to focus on much improvement over StyleGAN, but rather a different approach (Autoencoders) that can achieve similar results as StyleGAN.