It takes (only) two: adversarial generator-encoder networks
We present a new autoencoder-type architecture that is trainable in an unsupervised mode, sustains both generation and inference, and has the quality of conditional and unconditional samples boosted by adversarial learning. Unlike previous hybrids of autoencoders and adversarial networks, the advers...
Autori principali: | Ulyanov, D, Vedaldi, A, Lempitsky, V |
---|---|
Natura: | Conference item |
Pubblicazione: |
Association for the Advancement of Artificial Intelligence
2018
|
Documenti analoghi
Documenti analoghi
-
Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis
di: Ulyanov, D, et al.
Pubblicazione: (2017) -
Texture networks: Feed-forward synthesis of textures and stylized images
di: Ulyanov, D, et al.
Pubblicazione: (2016) -
Deep image prior
di: Ulyanov, D, et al.
Pubblicazione: (2018) -
Deep image prior
di: Ulyanov, D, et al.
Pubblicazione: (2020) -
The devil is in the details: an evaluation of recent feature encoding methods
di: Chatfield, K, et al.
Pubblicazione: (2011)