Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search

研究成果: Conference contribution

13 被引用数 (Scopus)

抄録

Researchers have applied deep neural networks to image restoration tasks, in which they proposed various network architectures, loss functions, and training methods. In particular, adversarial training, which is employed in recent studies, seems to be a key ingredient to success. In this paper, we show that simple convolutional autoencoders (CAEs) built upon only standard network components, i.e., convolutional layers and skip connections, can outperform the state-of-the-art methods which employ adversarial training and sophisticated loss functions. The secret is to search for good architectures using an evolutionary algorithm. All we did was to train the optimized CAEs by minimizing the l2 loss between reconstructed images and their ground truths using the ADAM optimizer. Our experimental results show that this approach achieves 27.8 dB peak signal to noise ratio (PSNR) on the CelebA dataset and 33.3 dB on the SVHN dataset, compared to 22.8 dB and 19.0 dB provided by the former state-of-the-art methods, respectively.

本文言語English
ホスト出版物のタイトル35th International Conference on Machine Learning, ICML 2018
編集者Andreas Krause, Jennifer Dy
出版社International Machine Learning Society (IMLS)
ページ7592-7601
ページ数10
ISBN(電子版)9781510867963
出版ステータスPublished - 2018 1 1
イベント35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden
継続期間: 2018 7 102018 7 15

出版物シリーズ

名前35th International Conference on Machine Learning, ICML 2018
11

Other

Other35th International Conference on Machine Learning, ICML 2018
国/地域Sweden
CityStockholm
Period18/7/1018/7/15

ASJC Scopus subject areas

  • 計算理論と計算数学
  • 人間とコンピュータの相互作用
  • ソフトウェア

フィンガープリント

「Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル