Sparse Output Coding for Large-Scale Visual Recognition

Bin Zhao, Eric P. Xing; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 3350-3357

Many vision tasks require a multi-class classifier to discriminate multiple categories, on the order of hundreds or thousands. In this paper, we propose sparse output coding, a principled way for large-scale multi-class classification, by turning high-cardinality multi-class categorization into a bit-by-bit decoding problem. Specifically, sparse output coding is composed of two steps: efficient coding matrix learning with scalability to thousands of classes, and probabilistic decoding. Empirical results on object recognition and scene classification demonstrate the effectiveness of our proposed approach.