Hierarchical Convolutional Sparse Image Decomposition

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.

• Type: Conference
• Year: 2010
• Where: CVPR
• Authors: Matthew Zeiler, Dilip Krishnan, Graham Taylor, Rob Fergus
• Keywords: Computer Vision, CVPR 2010, Many Existing Feature Detectors, Mid-level Cues, Mid-level Image Representations