Taking a Deeper Look at Pedestrians
This addresses pedestrian detection for computer vision applications, presenting an incremental improvement by optimizing convnet architectures and training data.
The paper tackles pedestrian detection using convolutional neural networks (convnets), achieving competitive performance on the Caltech and KITTI datasets without explicit modeling like parts or occlusion, with top results on Caltech setups and competitive performance even against detectors using additional test-time data.
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.