PointOBB: Learning Oriented Object Detection via Single Point Supervision

TL;DR

PointOBB introduces a novel single point-supervised method for oriented object detection, effectively predicting oriented bounding boxes in aerial images by leveraging multi-view strategies and self-supervised learning.

Contribution

It is the first single point-based method for oriented bounding box generation, integrating multi-view learning and self-supervised angle prediction.

Findings

Outperforms existing point-supervised baselines.

Achieves promising results on DIOR-R and DOTA-v1.0 datasets.

Effectively predicts oriented bounding boxes in aerial images.

Abstract

Single point-supervised object detection is gaining attention due to its cost-effectiveness. However, existing approaches focus on generating horizontal bounding boxes (HBBs) while ignoring oriented bounding boxes (OBBs) commonly used for objects in aerial images. This paper proposes PointOBB, the first single Point-based OBB generation method, for oriented object detection. PointOBB operates through the collaborative utilization of three distinctive views: an original view, a resized view, and a rotated/flipped (rot/flp) view. Upon the original view, we leverage the resized and rot/flp views to build a scale augmentation module and an angle acquisition module, respectively. In the former module, a Scale-Sensitive Consistency (SSC) loss is designed to enhance the deep network's ability to perceive the object scale. For accurate object angle predictions, the latter module incorporates self-supervised learning to predict angles, which is associated with a scale-guided Dense-to-Sparse (DS) matching strategy for aggregating dense angles corresponding to sparse objects. The resized and rot/flp views are switched using a progressive multi-view switching strategy during training to achieve coupled optimization of scale and angle. Experimental results on the DIOR-R and DOTA-v1.0 datasets demonstrate that PointOBB achieves promising performance, and significantly outperforms potential point-supervised baselines.