Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction

[leo-p]

https://pdfs.semanticscholar.org/1c6d/990c80e60aa0b0059415444cdf94b3574f0f.pdf

We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms. A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches. Initializing a CNN with filters of a trained CAE stack yields superior performance on a digit (MNIST) and an object recognition (CIFAR10) benchmark.

[leo-p]

Summary:

• Dataset: MNIST and SVHN.
• Objective: Introduces the Convolutional Auto-Encoder, a hierarchical unsupervised feature extractor.

Architecture:

Uses convolutions to generate an encoding of the image and then decodes it and do a pixel-wise comparison. Used to initializes CNN.

Results:

Old article, not really relevant nowadays. They don't speak about the deconvolution part.