Deconvolutional Networks

[leo-p]

http://www.matthewzeiler.com/pubs/cvpr2010/cvpr2010.pdf

Building robust low and mid-level image representations, beyond edge primitives, is a long-standing goal in vision. Many existing feature detectors spatially pool edge information which destroys cues such as edge intersections, parallelism and symmetry. We present a learning framework where features that capture these mid-level cues spontaneously emerge from image data. Our approach is based on the convolutional decomposition of images under a sparsity constraint and is totally unsupervised. By building a hierarchy of such decompositions we can learn rich feature sets that are a robust image representation for both the analysis and synthesis of images.

[leo-p]

Summary:

• Objective: Define a new deconvolution layer.

Results:

Not really interesting except from the fact that it first introduces deconvolution layers which are very ill-name as they are not actual deconvolution but instead a transposed convolution or also called a fractionally strided convolutions.

Visualization for other operations can be seen here corresponding to A guide to convolution arithmetic for deep learning.