Semantic Part Segmentation using Compositional Model combining Shape and Appearance
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,...
| Main Authors: | , |
|---|---|
| Format: | Technical Report |
| Language: | en_US |
| Published: |
Center for Brains, Minds and Machines (CBMM), arXiv
2015
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/100197 |
| _version_ | 1811078773707112448 |
|---|---|
| author | Wang, Jianyu Yuille, Alan L. |
| author_facet | Wang, Jianyu Yuille, Alan L. |
| author_sort | Wang, Jianyu |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T11:05:16Z |
| format | Technical Report |
| id | mit-1721.1/100197 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:05:16Z |
| publishDate | 2015 |
| publisher | Center for Brains, Minds and Machines (CBMM), arXiv |
| record_format | dspace |
| spelling | mit-1721.1/1001972019-04-11T03:55:15Z Semantic Part Segmentation using Compositional Model combining Shape and Appearance Wang, Jianyu Yuille, Alan L. Semantic Part Segmentation Object Recognition Compositional Models Artificial Intelligence 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. This work was supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award CCF-1231216. 2015-12-11T22:07:28Z 2015-12-11T22:07:28Z 2015-06-08 Technical Report Working Paper Other http://hdl.handle.net/1721.1/100197 arXiv:1412.6124 en_US CBMM Memo Series;032 Attribution-NonCommercial 3.0 United States http://creativecommons.org/licenses/by-nc/3.0/us/ application/pdf Center for Brains, Minds and Machines (CBMM), arXiv |
| spellingShingle | Semantic Part Segmentation Object Recognition Compositional Models Artificial Intelligence Wang, Jianyu Yuille, Alan L. Semantic Part Segmentation using Compositional Model combining Shape and Appearance |
| title | Semantic Part Segmentation using Compositional Model combining Shape and Appearance |
| title_full | Semantic Part Segmentation using Compositional Model combining Shape and Appearance |
| title_fullStr | Semantic Part Segmentation using Compositional Model combining Shape and Appearance |
| title_full_unstemmed | Semantic Part Segmentation using Compositional Model combining Shape and Appearance |
| title_short | Semantic Part Segmentation using Compositional Model combining Shape and Appearance |
| title_sort | semantic part segmentation using compositional model combining shape and appearance |
| topic | Semantic Part Segmentation Object Recognition Compositional Models Artificial Intelligence |
| url | http://hdl.handle.net/1721.1/100197 |
| work_keys_str_mv | AT wangjianyu semanticpartsegmentationusingcompositionalmodelcombiningshapeandappearance AT yuillealanl semanticpartsegmentationusingcompositionalmodelcombiningshapeandappearance |