Semantic Part Segmentation using Compositional Model combining Shape and Appearance
Author(s)
Wang, Jianyu; Yuille, Alan L.
DownloadCBMM-Memo-032.pdf (6.493Mb)
Terms of use
Metadata
Show full item recordAbstract
In this paper, we study the problem of semantic part segmentation for animals. This is more challenging than standard object detection, object segmentation and pose estimation tasks because semantic parts of animals often have similar appearance and highly varying shapes. To tackle these challenges, we build a mixture of compositional models to represent the object boundary and the boundaries of semantic parts. And we incorporate edge, appearance, and semantic part cues into the compositional model. Given part-level segmentation annotation, we develop a novel algorithm 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.
Date issued
2015-06-08Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1412.6124
Series/Report no.
CBMM Memo Series;032
Keywords
Semantic Part Segmentation, Object Recognition, Compositional Models, Artificial Intelligence
Collections
The following license files are associated with this item: