The Role of Context Selection in Object Detection

Ruichi Yu, Xi Chen, Vlad Morariu and Larry Davis

Abstract

We investigate the reasons why context in object detection has limited utility by isolating and evaluating the predictive power of different context cues under ideal conditions in which context provided by an oracle. Based on this study, we propose a region-based context re-scoring method with dynamic context selection to remove noise and emphasize informative context. We introduce latent indicator variables to select (or ignore) potential contextual regions, and learn the selection strategy with latent-SVM. We conduct experiments to evaluate the performance of the proposed context selection method on the SUN RGB-D dataset. The method achieves a significant improvement in terms of mean average precision (mAP), compared with both appearance based detectors and a conventional context model without the selection scheme.

Session

Recognition

Files

Extended Abstract (PDF, 636K)
Paper (PDF, 2M)
Supplemental Materials (PDF, 3M)

DOI

10.5244/C.30.133
https://dx.doi.org/10.5244/C.30.133

Citation

Bibtex

        @inproceedings{BMVC2016_133,
        	title={The Role of Context Selection in Object Detection},
        	author={Ruichi Yu, Xi Chen, Vlad Morariu and Larry Davis},
        	year={2016},
        	month={September},
        	pages={133.1-133.13},
        	articleno={133},
        	numpages={13},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.133},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.133}
        }