Large-scale image classification using supervised spatial encoder

Spatial pyramid matching (SPM) component is part of most state-of-art image classification methods. SPM encodes spatial distribution of image features, in an un-supervised fashion, by partitioning an image into regions at multiple scales and concatenating feature vectors for these regions. In this paper we propose to replace the unsupervised SPM procedure with a supervised two-stage feature selection that requires the image partitioned at a single scale. Experimental results show the proposed method performs statistically significantly better than the SPM baseline.