Reconstructive sparse code transfer for contour detection and semantic labeling. ACCV

Abstract. We frame the task of predicting a semantic labeling as a sparse reconstruction procedure that applies a target-specific learned transfer function to a generic deep sparse code representation of an im-age. This strategy partitions training into two distinct stages. First, in an unsupervised manner, we learn a set of dictionaries optimized for sparse coding of image patches. These generic dictionaries minimize er-ror with respect to representing image appearance and are independent of any particular target task. We train a multilayer representation via recursive sparse dictionary learning on pooled codes output by earlier layers. Second, we encode all training images with the generic dictionar-ies and learn a transfer function that optimizes reconstruction of patches extracted from annotated ground-truth given the sparse codes of their corresponding image patches. At test time, we encode a novel image using the generic dictionaries and then reconstruct using the transfer function. The output reconstruction is a semantic labeling of the test image