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...
主要な著者: | Ulyanov, D, Vedaldi, A, Lempitsky, V |
---|---|
フォーマット: | Conference item |
出版事項: |
Association for the Advancement of Artificial Intelligence
2018
|
類似資料
-
Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis
著者:: Ulyanov, D, 等
出版事項: (2017) -
Texture networks: Feed-forward synthesis of textures and stylized images
著者:: Ulyanov, D, 等
出版事項: (2016) -
Deep image prior
著者:: Ulyanov, D, 等
出版事項: (2018) -
Deep image prior
著者:: Ulyanov, D, 等
出版事項: (2020) -
The devil is in the details: an evaluation of recent feature encoding methods
著者:: Chatfield, K, 等
出版事項: (2011)