Taking a Deeper Look at Pedestrians

TL;DR

This paper investigates the effectiveness of convolutional neural networks for pedestrian detection, demonstrating that well-designed convnets can achieve competitive performance without complex modeling or additional test-time data.

Contribution

The study shows that simple convnet architectures, with careful training and data usage, can outperform traditional methods in pedestrian detection tasks.

Findings

Convnets can reach top performance on Caltech and KITTI datasets.

Additional training data improves convnet performance significantly.

Convnets outperform some methods that rely on extra test-time data.

Abstract

In this paper we study the use of convolutional neural networks (convnets) for the task of pedestrian detection. Despite their recent diverse successes, convnets historically underperform compared to other pedestrian detectors. We deliberately omit explicitly modelling the problem into the network (e.g. parts or occlusion modelling) and show that we can reach competitive performance without bells and whistles. In a wide range of experiments we analyse small and big convnets, their architectural choices, parameters, and the influence of different training data, including pre-training on surrogate tasks. We present the best convnet detectors on the Caltech and KITTI dataset. On Caltech our convnets reach top performance both for the Caltech1x and Caltech10x training setup. Using additional data at training time our strongest convnet model is competitive even to detectors that use additional data (optical flow) at test time.