Paper Info
Title
Point-to-Box Network for Accurate Object Detection via Single Point Supervision.
Abstract
Object detection using single point supervision has received increasing attention over the years. However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large. In this paper, we attribute such a large performance gap to the failure of generating high-quality proposal bags which are crucial for multiple instance learning (MIL). To address this problem, we introduce a lightweight alternative to the off-the-shelf proposal (OTSP) method and thereby create the Point-to-Box Network (P2BNet), which can construct an inter-objects balanced proposal bag by generating proposals in an anchor-like way. By fully investigating the accurate position information, P2BNet further constructs an instance-level bag, avoiding the mixture of multiple objects. Finally, a coarse-to-fine policy in a cascade fashion is utilized to improve the IoU between proposals and ground-truth (GT). Benefiting from these strategies, P2BNet is able to produce high-quality instance-level bags for object detection. P2BNet improves the mean average precision (AP) by more than 50% relative to the previous best PSOD method on the MS COCO dataset. It also demonstrates the great potential to bridge the performance gap between point supervised and bounding-box supervised detectors. The code will be released at www.github.com/ucas-vg/P2BNet.
Year
DOI
Venue
2022
10.1007/978-3-031-20077-9_4
European Conference on Computer Vision
Keywords
DocType
Citations 
Object detection,Single point annotation,Point supervised object detection
Conference
0
PageRank 
References 
Authors
0.34
0
10
Name
Order
Citations
PageRank
Pengfei Chen100.68
Xuehui Yu201.69
Xumeng Han300.34
Najmul Hassan400.68
Kai Wang51734195.03
Jiachen Li600.34
Jian Zhao700.68
Honghui Shi818320.24
Zhenjun Han917616.40
Qixiang Ye1001.35