Abstract

In this paper, we study the problem of semantic part seg-mentation for animals. This is more challenging than standard object detection, object segmentation and pose estimation tasks because semantic parts of animals often have sim-ilar appearance and highly varying shapes. To tackle thesechallenges, we build a mixture of compositional models torepresent the object boundary and the boundaries of seman-tic parts. And we incorporate edge, appearance, and se-mantic part cues into the compositional model. Given partlevel segmentation annotation, we develop a novel algo-rithm to learn a mixture of compositional models under various poses and viewpoints for certain animal classes. Furthermore, a linear complexity algorithm is offered for efficient inference of the compositional model using dynamic programming. We evaluate our method for horse and cow using a newly annotated dataset on Pascal VOC 2010 which has pixelwise part labels. Experimental results demonstrate the effectiveness of our method.