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...
Үндсэн зохиолчид: | Ulyanov, D, Vedaldi, A, Lempitsky, V |
---|---|
Формат: | Conference item |
Хэвлэсэн: |
Association for the Advancement of Artificial Intelligence
2018
|
Ижил төстэй зүйлс
Ижил төстэй зүйлс
-
Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis
-н: Ulyanov, D, зэрэг
Хэвлэсэн: (2017) -
Texture networks: Feed-forward synthesis of textures and stylized images
-н: Ulyanov, D, зэрэг
Хэвлэсэн: (2016) -
Deep image prior
-н: Ulyanov, D, зэрэг
Хэвлэсэн: (2018) -
Deep image prior
-н: Ulyanov, D, зэрэг
Хэвлэсэн: (2020) -
The devil is in the details: an evaluation of recent feature encoding methods
-н: Chatfield, K, зэрэг
Хэвлэсэн: (2011)