Single-Shot Refinement Neural Network for Object Detection

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

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection COCO test-dev RefineDet512+ (VGG-16) box AP 37.6 # 185
AP50 58.7 # 141
AP75 40.8 # 143
APS 22.7 # 120
APM 40.3 # 141
APL 48.3 # 144
Hardware Burden None # 1
Operations per network pass None # 1
Object Detection COCO test-dev RefineDet512+ (ResNet-101) box AP 41.8 # 150
AP50 62.9 # 102
AP75 45.7 # 114
APS 25.6 # 93
APM 45.1 # 112
APL 54.1 # 112
Hardware Burden None # 1
Operations per network pass None # 1
Object Detection COCO test-dev RefineDet512 (ResNet-101) box AP 36.4 # 191
AP50 57.5 # 147
AP75 39.5 # 146
APS 16.6 # 144
APM 39.9 # 143
APL 51.4 # 130
Hardware Burden None # 1
Operations per network pass None # 1
Object Detection COCO test-dev RefineDet512 (VGG-16) box AP 33 # 200
AP50 54.5 # 151
AP75 35.5 # 148
APS 16.3 # 145
APM 36.3 # 146
APL 44.3 # 147
Hardware Burden None # 1
Operations per network pass None # 1

Methods