What Can Help Pedestrian Detection?

CVPR 2017  ·  Jiayuan Mao, Tete Xiao, Yuning Jiang, Zhimin Cao ·

Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods. However, there is still a lack of studies on whether and how CNN-based pedestrian detectors can benefit from these extra features. The first contribution of this paper is exploring this issue by aggregating extra features into CNN-based pedestrian detection framework. Through extensive experiments, we evaluate the effects of different kinds of extra features quantitatively. Moreover, we propose a novel network architecture, namely HyperLearner, to jointly learn pedestrian detection as well as the given extra feature. By multi-task training, HyperLearner is able to utilize the information of given features and improve detection performance without extra inputs in inference. The experimental results on multiple pedestrian benchmarks validate the effectiveness of the proposed HyperLearner.

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract
No code implementations yet. Submit your code now

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Pedestrian Detection Caltech HyperLearner Reasonable Miss Rate 5.5 # 13


No methods listed for this paper. Add relevant methods here