PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Peiyuan, Luo, Junwei, Yang, Xue, Yu, Yi, Li, Qingyun, Zhou, Yue, Jia, Xiaosong, Lu, Xudong, Chen, Jingdong, Li, Xiang, Yan, Junchi, Li, Yansheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908377469157376
author Zhang, Peiyuan
Luo, Junwei
Yang, Xue
Yu, Yi
Li, Qingyun
Zhou, Yue
Jia, Xiaosong
Lu, Xudong
Chen, Jingdong
Li, Xiang
Yan, Junchi
Li, Yansheng
author_facet Zhang, Peiyuan
Luo, Junwei
Yang, Xue
Yu, Yi
Li, Qingyun
Zhou, Yue
Jia, Xiaosong
Lu, Xudong
Chen, Jingdong
Li, Xiang
Yan, Junchi
Li, Yansheng
contents With the growing demand for oriented object detection (OOD), recent studies on point-supervised OOD have attracted significant interest. In this paper, we propose PointOBB-v3, a stronger single point-supervised OOD framework. Compared to existing methods, it generates pseudo rotated boxes without additional priors and incorporates support for the end-to-end paradigm. PointOBB-v3 functions by integrating three unique image views: the original view, a resized view, and a rotated/flipped (rot/flp) view. Based on the views, a scale augmentation module and an angle acquisition module are constructed. In the first module, a Scale-Sensitive Consistency (SSC) loss and a Scale-Sensitive Feature Fusion (SSFF) module are introduced to improve the model's ability to estimate object scale. To achieve precise angle predictions, the second module employs symmetry-based self-supervised learning. Additionally, we introduce an end-to-end version that eliminates the pseudo-label generation process by integrating a detector branch and introduces an Instance-Aware Weighting (IAW) strategy to focus on high-quality predictions. We conducted extensive experiments on the DIOR-R, DOTA-v1.0/v1.5/v2.0, FAIR1M, STAR, and RSAR datasets. Across all these datasets, our method achieves an average improvement in accuracy of 3.56% in comparison to previous state-of-the-art methods. The code will be available at https://github.com/ZpyWHU/PointOBB-v3.
format Preprint
id arxiv_https___arxiv_org_abs_2501_13898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection
Zhang, Peiyuan
Luo, Junwei
Yang, Xue
Yu, Yi
Li, Qingyun
Zhou, Yue
Jia, Xiaosong
Lu, Xudong
Chen, Jingdong
Li, Xiang
Yan, Junchi
Li, Yansheng
Computer Vision and Pattern Recognition
Artificial Intelligence
With the growing demand for oriented object detection (OOD), recent studies on point-supervised OOD have attracted significant interest. In this paper, we propose PointOBB-v3, a stronger single point-supervised OOD framework. Compared to existing methods, it generates pseudo rotated boxes without additional priors and incorporates support for the end-to-end paradigm. PointOBB-v3 functions by integrating three unique image views: the original view, a resized view, and a rotated/flipped (rot/flp) view. Based on the views, a scale augmentation module and an angle acquisition module are constructed. In the first module, a Scale-Sensitive Consistency (SSC) loss and a Scale-Sensitive Feature Fusion (SSFF) module are introduced to improve the model's ability to estimate object scale. To achieve precise angle predictions, the second module employs symmetry-based self-supervised learning. Additionally, we introduce an end-to-end version that eliminates the pseudo-label generation process by integrating a detector branch and introduces an Instance-Aware Weighting (IAW) strategy to focus on high-quality predictions. We conducted extensive experiments on the DIOR-R, DOTA-v1.0/v1.5/v2.0, FAIR1M, STAR, and RSAR datasets. Across all these datasets, our method achieves an average improvement in accuracy of 3.56% in comparison to previous state-of-the-art methods. The code will be available at https://github.com/ZpyWHU/PointOBB-v3.
title PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2501.13898