Single-Shot Refinement Neural Network for Object Detection

CVPR 2018  ·  Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li ·

For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, in this paper, we propose a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods... RefineDet consists of two inter-connected modules, namely, the anchor refinement module and the object detection module. Specifically, the former aims to (1) filter out negative anchors to reduce search space for the classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes the refined anchors as the input from the former to further improve the regression and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multi-task loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO demonstrate that RefineDet achieves state-of-the-art detection accuracy with high efficiency. Code is available at https://github.com/sfzhang15/RefineDet read more

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection COCO test-dev RefineDet512+ (VGG-16) box AP 37.6 # 158
AP50 58.7 # 129
AP75 40.8 # 133
APS 22.7 # 114
APM 40.3 # 134
APL 48.3 # 137
Object Detection COCO test-dev RefineDet512+ (ResNet-101) box AP 41.8 # 125
AP50 62.9 # 92
AP75 45.7 # 104
APS 25.6 # 88
APM 45.1 # 105
APL 54.1 # 105
Object Detection COCO test-dev RefineDet512 (VGG-16) box AP 33 # 171
AP50 54.5 # 138
AP75 35.5 # 138
APS 16.3 # 139
APM 36.3 # 139
APL 44.3 # 139
Object Detection COCO test-dev RefineDet512 (ResNet-101) box AP 36.4 # 164
AP50 57.5 # 135
AP75 39.5 # 136
APS 16.6 # 138
APM 39.9 # 136
APL 51.4 # 123
Object Detection PASCAL VOC 2007 RefineDet512+ MAP 83.8% # 3

Methods