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...
Автори: | Ulyanov, D, Vedaldi, A, Lempitsky, V |
---|---|
Формат: | Conference item |
Опубліковано: |
Association for the Advancement of Artificial Intelligence
2018
|
Схожі ресурси
Схожі ресурси
-
Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis
за авторством: Ulyanov, D, та інші
Опубліковано: (2017) -
Texture networks: Feed-forward synthesis of textures and stylized images
за авторством: Ulyanov, D, та інші
Опубліковано: (2016) -
Deep image prior
за авторством: Ulyanov, D, та інші
Опубліковано: (2018) -
Deep image prior
за авторством: Ulyanov, D, та інші
Опубліковано: (2020) -
The devil is in the details: an evaluation of recent feature encoding methods
за авторством: Chatfield, K, та інші
Опубліковано: (2011)