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...
Hoofdauteurs: | Ulyanov, D, Vedaldi, A, Lempitsky, V |
---|---|
Formaat: | Conference item |
Gepubliceerd in: |
Association for the Advancement of Artificial Intelligence
2018
|
Gelijkaardige items
Advances in generative adversarial network
door: Wanliang WANG, et al.
Gepubliceerd in: (2018-02-01)
door: Wanliang WANG, et al.
Gepubliceerd in: (2018-02-01)
Gelijkaardige items
-
Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis
door: Ulyanov, D, et al.
Gepubliceerd in: (2017) -
Texture networks: Feed-forward synthesis of textures and stylized images
door: Ulyanov, D, et al.
Gepubliceerd in: (2016) -
Deep image prior
door: Ulyanov, D, et al.
Gepubliceerd in: (2018) -
Deep image prior
door: Ulyanov, D, et al.
Gepubliceerd in: (2020) -
The devil is in the details: an evaluation of recent feature encoding methods
door: Chatfield, K, et al.
Gepubliceerd in: (2011)