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...
Những tác giả chính: | Ulyanov, D, Vedaldi, A, Lempitsky, V |
---|---|
Định dạng: | Conference item |
Được phát hành: |
Association for the Advancement of Artificial Intelligence
2018
|
Những quyển sách tương tự
-
Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis
Bằng: Ulyanov, D, et al.
Được phát hành: (2017) -
Texture networks: Feed-forward synthesis of textures and stylized images
Bằng: Ulyanov, D, et al.
Được phát hành: (2016) -
Deep image prior
Bằng: Ulyanov, D, et al.
Được phát hành: (2018) -
Deep image prior
Bằng: Ulyanov, D, et al.
Được phát hành: (2020) -
The devil is in the details: an evaluation of recent feature encoding methods
Bằng: Chatfield, K, et al.
Được phát hành: (2011)