@article{creswellGenerativeAdversarialNetworks2017,
  archivePrefix = {arXiv},
  eprinttype = {arxiv},
  eprint = {1710.07035},
  primaryClass = {cs},
  title = {Generative {{Adversarial Networks}}: {{An Overview}}},
  url = {http://arxiv.org/abs/1710.07035},
  shorttitle = {Generative {{Adversarial Networks}}},
  abstract = {Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image synthesis, semantic image editing, style transfer, image super-resolution and classification. The aim of this review paper is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible. In addition to identifying different methods for training and constructing GANs, we also point to remaining challenges in their theory and application.},
  urldate = {2017-11-03},
  date = {2017-10-19},
  keywords = {Computer Science - Computer Vision and Pattern Recognition},
  author = {Creswell, Antonia and White, Tom and Dumoulin, Vincent and Arulkumaran, Kai and Sengupta, Biswa and Bharath, Anil A.},
  file = {/home/dimitri/Nextcloud/Zotero/storage/MP87U6RA/Creswell et al. - 2017 - Generative Adversarial Networks An Overview.pdf;/home/dimitri/Nextcloud/Zotero/storage/4TWDAP5A/1710.html}
}

{"_id":"KWp4jox4cieY4YgmR","bibbaseid":"creswell-white-dumoulin-arulkumaran-sengupta-bharath-generativeadversarialnetworksanoverview","authorIDs":[],"author_short":["Creswell, A.","White, T.","Dumoulin, V.","Arulkumaran, K.","Sengupta, B.","Bharath, A. A."],"bibdata":{"bibtype":"article","type":"article","archiveprefix":"arXiv","eprinttype":"arxiv","eprint":"1710.07035","primaryclass":"cs","title":"Generative Adversarial Networks: An Overview","url":"http://arxiv.org/abs/1710.07035","shorttitle":"Generative Adversarial Networks","abstract":"Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image synthesis, semantic image editing, style transfer, image super-resolution and classification. The aim of this review paper is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible. In addition to identifying different methods for training and constructing GANs, we also point to remaining challenges in their theory and application.","urldate":"2017-11-03","date":"2017-10-19","keywords":"Computer Science - Computer Vision and Pattern Recognition","author":[{"propositions":[],"lastnames":["Creswell"],"firstnames":["Antonia"],"suffixes":[]},{"propositions":[],"lastnames":["White"],"firstnames":["Tom"],"suffixes":[]},{"propositions":[],"lastnames":["Dumoulin"],"firstnames":["Vincent"],"suffixes":[]},{"propositions":[],"lastnames":["Arulkumaran"],"firstnames":["Kai"],"suffixes":[]},{"propositions":[],"lastnames":["Sengupta"],"firstnames":["Biswa"],"suffixes":[]},{"propositions":[],"lastnames":["Bharath"],"firstnames":["Anil","A."],"suffixes":[]}],"file":"/home/dimitri/Nextcloud/Zotero/storage/MP87U6RA/Creswell et al. - 2017 - Generative Adversarial Networks An Overview.pdf;/home/dimitri/Nextcloud/Zotero/storage/4TWDAP5A/1710.html","bibtex":"@article{creswellGenerativeAdversarialNetworks2017,\n archivePrefix = {arXiv},\n eprinttype = {arxiv},\n eprint = {1710.07035},\n primaryClass = {cs},\n title = {Generative {{Adversarial Networks}}: {{An Overview}}},\n url = {http://arxiv.org/abs/1710.07035},\n shorttitle = {Generative {{Adversarial Networks}}},\n abstract = {Generative adversarial networks (GANs) provide a way to learn deep representations without extensively annotated training data. They achieve this through deriving backpropagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in a variety of applications, including image synthesis, semantic image editing, style transfer, image super-resolution and classification. The aim of this review paper is to provide an overview of GANs for the signal processing community, drawing on familiar analogies and concepts where possible. In addition to identifying different methods for training and constructing GANs, we also point to remaining challenges in their theory and application.},\n urldate = {2017-11-03},\n date = {2017-10-19},\n keywords = {Computer Science - Computer Vision and Pattern Recognition},\n author = {Creswell, Antonia and White, Tom and Dumoulin, Vincent and Arulkumaran, Kai and Sengupta, Biswa and Bharath, Anil A.},\n file = {/home/dimitri/Nextcloud/Zotero/storage/MP87U6RA/Creswell et al. - 2017 - Generative Adversarial Networks An Overview.pdf;/home/dimitri/Nextcloud/Zotero/storage/4TWDAP5A/1710.html}\n}\n\n","author_short":["Creswell, A.","White, T.","Dumoulin, V.","Arulkumaran, K.","Sengupta, B.","Bharath, A. A."],"key":"creswellGenerativeAdversarialNetworks2017","id":"creswellGenerativeAdversarialNetworks2017","bibbaseid":"creswell-white-dumoulin-arulkumaran-sengupta-bharath-generativeadversarialnetworksanoverview","role":"author","urls":{"Paper":"http://arxiv.org/abs/1710.07035"},"keyword":["Computer Science - Computer Vision and Pattern Recognition"],"downloads":0},"bibtype":"article","biburl":"https://raw.githubusercontent.com/dlozeve/newblog/master/bib/all.bib","creationDate":"2020-01-08T20:39:39.116Z","downloads":0,"keywords":["computer science - computer vision and pattern recognition"],"search_terms":["generative","adversarial","networks","overview","creswell","white","dumoulin","arulkumaran","sengupta","bharath"],"title":"Generative Adversarial Networks: An Overview","year":null,"dataSources":["3XqdvqRE7zuX4cm8m"]}