The Role of Context for Object Detection and Semantic Segmentation in the Wild

被引：955

作者：

Mottaghi, Roozbeh ^{[1
]}

Chen, Xianjie ^{[2
]}

Liu, Xiaobai ^{[2
]}

Cho, Nam-Gyu ^{[3
]}

Lee, Seong-Whan ^{[3
]}

Fidler, Sanja ^{[4
]}

Urtasun, Raquel ^{[4
]}

Yuille, Alan ^{[2
]}

机构：

[1] Stanford Univ, Stanford, CA 94305 USA

[2] Univ Calif Los Angeles, Los Angeles, CA 90024 USA

[3] Korea Univ, Taejon, South Korea

[4] Univ Toronto, Toronto, ON M5S 1A1, Canada

来源：

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2014年

关键词：

D O I：

10.1109/CVPR.2014.119

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches. Towards this goal, we label every pixel of PASCAL VOC 2010 detection challenge with a semantic category. We believe this data will provide plenty of challenges to the community, as it contains 520 additional classes for semantic segmentation and object detection. Our analysis shows that nearest neighbor based approaches perform poorly on semantic segmentation of contextual classes, showing the variability of PASCAL imagery. Furthermore, improvements of existing contextual models for detection is rather modest. In order to push forward the performance in this difficult scenario, we propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. We show that this contextual reasoning significantly helps in detecting objects at all scales.

引用

页码：891 / 898

页数：8