Exploit All the Layers: Fast and Accurate CNN Object Detector

MOT17-01 MOT17-03 MOT17-06 MOT17-07 MOT17-08 MOT17-12 MOT17-14

Short name:

SDP

Benchmark:

Description:

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) layer-wise 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.

Hardware:

3GHz

Detector:

Public

Last submitted:

February 21, 2017 (1 year ago)

Published:

April 15, 2017 at 07:43:32 CET

Submissions:

3

Open source:

No

Project page / code:

n/a

Reference:

F. Yang, W. Choi, Y. Lin. Exploit All the Layers: Fast and Accurate CNN Object Detector With Scale Dependent Pooling and Cascaded Rejection Classifiers. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

Benchmark performance:

APSpecifications
0.813GHz

Detailed performance:

Sequence AP
MOT17-010.7011
MOT17-030.9064
MOT17-060.7239
MOT17-070.7981
MOT17-080.8997
MOT17-120.7194
MOT17-140.5132

Raw data:


SDP