Scale-aware Fast R-CNN for Pedestrian Detection

TL;DR

This paper introduces SAF R-CNN, a scale-aware framework for pedestrian detection that uses multiple sub-networks for different scales and adaptively combines their outputs, significantly improving detection accuracy across varied scales.

Contribution

The paper proposes a novel scale-aware detection framework with multiple sub-networks and an adaptive combination mechanism, addressing large scale variance in pedestrian detection.

Findings

Achieves state-of-the-art results on Caltech, INRIA, and ETH datasets.

Demonstrates robustness to large scale variance in pedestrian detection.

Outperforms existing methods in challenging scenarios.

Abstract

In this work, we consider the problem of pedestrian detection in natural scenes. Intuitively, instances of pedestrians with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intra-category variance in features, may severely hurt the performance of modern object instance detection methods. We argue that this issue can be substantially alleviated by the divide-and-conquer philosophy. Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework. The model introduces multiple built-in sub-networks which detect pedestrians with scales from disjoint ranges. Outputs from all the sub-networks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales, via a gate function defined over the sizes of object proposals. Extensive evaluations on several challenging pedestrian detection datasets well demonstrate the effectiveness of the proposed SAF R-CNN. Particularly, our method achieves state-of-the-art performance on Caltech, INRIA, and ETH, and obtains competitive results on KITTI.