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

Fan Yang, Wongun Choi, Yuanqing Lin
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
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
more » ... 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 dblp:conf/cvpr/YangCL16 fatcat:7h7ry3dgonaxtnsypvsr52rc2e