paper-with-me

홈 › Papers

Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision

2023-11-23 · CVPR 2024 1 · Yi Yu, Xue Yang, Qingyun Li, Feipeng Da, Jifeng Dai, Yu Qiao, Junchi Yan

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.

📄 PDF Abstract BibTeX arXiv:2311.14758

Code (2)

open-mmlab/mmrotate 공식 구현 pytorch
yuyi1005/point2rbox-mmrotate 공식 구현 pytorch

Tasks

Objectobject-detectionObject DetectionOriented Object Detection

Similar Papers 제목 키워드 기반

Domain knowledge-informed Synthetic fault sample generation with Health Data Map for cross-domain Planetary Gearbox Fault Diagnosis

2023-05-31 · Jong Moon Ha, Olga Fink

Extensive research has been conducted on fault diagnosis of planetary gearboxes using vibration signals and deep learning (DL) approaches. However, DL-based methods are susceptible to the domain shift problem caused by v…

Domain AdaptationFault Diagnosis

H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection

2023-09-21 · NeurIPS 2023 11

With the rapidly increasing demand for oriented object detection, e.g. in autonomous driving and remote sensing, the recently proposed paradigm involving weakly-supervised detector H2RBox for learning rotated box (RBox) …

Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances

2025-02-06 · CVPR 2025 1 · Yi Yu, Botao Ren, Peiyuan Zhang, Mingxin Liu 외

With the rapidly increasing demand for oriented object detection (OOD), recent research involving weakly-supervised detectors for learning OOD from point annotations has gained great attention. In this paper, we rethink …

object-detectionObject DetectionOriented Object Detection

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization

2025-09-30 · Teng Zhang, Ziqian Fan, Mingxin Liu, Xin Zhang 외 arxiv

Driven by the growing need for Oriented Object Detection (OOD), learning from point annotations under a weakly-supervised framework has emerged as a promising alternative to costly and laborious manual labeling. In this …

Object Detection

P2RBox: Point Prompt Oriented Object Detection with SAM

2023-11-22 · Guangming Cao, Xuehui Yu, Wenwen Yu, Xumeng Han 외

Single-point annotation in oriented object detection of remote sensing scenarios is gaining increasing attention due to its cost-effectiveness. However, due to the granularity ambiguity of points, there is a significant …

Objectobject-detectionObject DetectionOriented Object Detection