What Can Help Pedestrian Detection?

TL;DR

This paper investigates how extra features can enhance CNN-based pedestrian detection, introduces a novel HyperLearner architecture for joint learning, and demonstrates improved performance through extensive experiments.

Contribution

It explores the integration of extra features into CNN detectors and proposes HyperLearner for joint learning without extra inference inputs.

Findings

HyperLearner improves detection accuracy on multiple benchmarks.

Extra features significantly enhance CNN pedestrian detectors.

Joint learning reduces reliance on additional inputs during inference.

Abstract

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.