Skip to content

Latest commit

 

History

History
17 lines (16 loc) · 1.2 KB

dl_23.md

File metadata and controls

17 lines (16 loc) · 1.2 KB

Split-brain autoencoders: unsupervised learning by cross-channel prediction

Richard Zhang, Phillip Isola, Alexei A. Efros (2017)

Key points

  • Two disjoint sub-networks for unsupervised representation learning
    • Each predicting one subset of the data channels from another
    • Together: features from entire input signal
    • Forcing the network to solve cross-prediction tasks --> induce representation that transfers well to unseen tasks
    • Split: grayscale and color channels or RGB-D
  • Regular autoencoder (AE): forced abstraction through bottleneck --> information loss
  • Context encoder: withhold part of the input (e.g. colorization, inpainting blocks of pixels)
    • Last one is difficult: image synthesis is difficult + domain gap (blocks vs full images at test time) + might only require low-level reasoning (bad representation learning)
    • However, colorization does work (due to spatial correspondence of gray and color)
  • Cross-channel encoders (of which colorization is an example): different channels not treated equally (one is for feature extraction, another is target) --> our solution comes in!
  • No need for bottleneck
  • Dropout on input to force abstraction
  • Pre-trained on full input data