Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision
CoRR(2023)
Abstract
With the rapidly increasing demand for oriented object detection (OOD), recent research involving weakly-supervised detectors for learning rotated box (RBox) from the horizontal box (HBox) has attracted more and more attention. In this paper, we explore a more challenging yet label-efficient setting, namely single point-supervised OOD, and present our approach called Point2RBox. Specifically, we propose to leverage two principles: 1) Synthetic pattern knowledge combination: By sampling around each labeled point on the image, we spread the object feature to synthetic visual patterns with known boxes to provide the knowledge for box regression. 2) Transform self-supervision: With a transformed input image (e.g. scaled/rotated), the output RBoxes are trained to follow the same transformation so that the network can perceive the relative size/rotation between objects. The detector is further enhanced by a few devised techniques to cope with peripheral issues, e.g. the anchor/layer assignment as the size of the object is not available in our point supervision setting. To our best knowledge, Point2RBox is the first end-to-end solution for point-supervised OOD. In particular, our method uses a lightweight paradigm, yet it achieves a competitive performance among point-supervised alternatives, 41.05%/27.62%/80.01% on DOTA/DIOR/HRSC datasets.
MoreTranslated text
Key words
Object Detection,Synthetic Patterns,Oriented Object Detection,Point Supervision,Input Image,Object Size,Learning Rate,Random Number,Intersection Over Union,Bounding Box,Aerial Images,Manual Annotation,Basic Patterns,Range Image,Center Of The Circle,Random Rotation,Target Training,Random Flipping,Feature Pyramid Network,Pseudo Labels,Black Edges,Basketball Court,ResNet-50 Backbone
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined