SEMANTIC SEGMENTATION VIA SPARSE CODING OVER HIERARCHICAL REGIONS

Overview & Synopsis

The purpose of this paper is segmenting objects in an image and assigning a predefined semantic label to each object. There are two areas of novelty in this paper. On one hand, hierarchical regions are used to guide semantic segmenta-tion instead of using single-level regions or multi-scale regions generated by multiple segmentations. On the other hand, sparse coding is introduced as high level description of the regions, which contributes to less quantization error than traditional bag-of-visual-words method. Experiments on the challenging Microsoft Research Cambridge dataset (MSRC 21) show that our algorithm achieves state-of-the-art performance.