A layer-wise training method for the convolutional autoencoder is used in (Masci, Jonathan, et al. "Stacked convolutional auto-encoders for hierarchical feature extraction." Artificial Neural Networks and Machine Learning–ICANN 2011 (2011): 52-59. ) This might help to achieve good results for deeper autoencoders.
bitraten
commented
7 years ago
A layer-wise training method for the convolutional autoencoder is used in (Masci, Jonathan, et al. "Stacked convolutional auto-encoders for hierarchical feature extraction." Artificial Neural Networks and Machine Learning–ICANN 2011 (2011): 52-59. ) This might help to achieve good results for deeper autoencoders.