Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

Abstract

In this paper, we investigate two new strategies to detect objects accurately and efficiently using deep convolutional neural network: 1) scale-dependent pooling and 2) layerwise cascaded rejection classifiers. The scale-dependent pooling (SDP) improves detection accuracy by exploiting appropriate convolutional features depending on the scale of candidate object proposals. The cascaded rejection classifiers (CRC) effectively utilize convolutional features and eliminate negative object proposals in a cascaded manner, which greatly speeds up the detection while maintaining high accuracy. In combination of the two, our method achieves significantly better accuracy compared to other state-of-the-arts in three challenging datasets, PASCAL object detection challenge, KITTI object detection benchmark and newly collected Inner-city dataset, while being more efficient.

DOI: 10.1109/CVPR.2016.234

Extracted Key Phrases

05020162017
Citations per Year

66 Citations

Semantic Scholar estimates that this publication has 66 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Yang2016ExploitAT, title={Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers}, author={Fan Yang and Wongun Choi and Yuanqing Lin}, journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2016}, pages={2129-2137} }