Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detection

TL;DR

This paper introduces SSP, a novel framework for point-supervised oriented object detection in remote sensing images, combining rule-based and data-driven methods to improve detection accuracy in densely packed scenes.

Contribution

The paper presents SSP, a unified framework that enhances point-supervised detection by integrating spatial partitioning and semantic information for better sample assignment and box extraction.

Findings

Achieves 45.78% mAP on DOTA-v1.0, surpassing state-of-the-art methods.

Improves detection performance when integrated with existing architectures like ORCNN and ReDet.

Demonstrates effectiveness in high-density remote sensing scenes.

Abstract

Recent remote sensing tech advancements drive imagery growth, making oriented object detection rapid development, yet hindered by labor-intensive annotation for high-density scenes. Oriented object detection with point supervision offers a cost-effective solution for densely packed scenes in remote sensing, yet existing methods suffer from inadequate sample assignment and instance confusion due to rigid rule-based designs. To address this, we propose SSP (Semantic-decoupled Spatial Partition), a unified framework that synergizes rule-driven prior injection and data-driven label purification. Specifically, SSP introduces two core innovations: 1) Pixel-level Spatial Partition-based Sample Assignment, which compactly estimates the upper and lower bounds of object scales and mines high-quality positive samples and hard negative samples through spatial partitioning of pixel maps. 2) Semantic Spatial Partition-based Box Extraction, which derives instances from spatial partitions modulated by semantic maps and reliably converts them into bounding boxes to form pseudo-labels for supervising the learning of downstream detectors. Experiments on DOTA-v1.0 and others demonstrate SSP\' s superiority: it achieves 45.78% mAP under point supervision, outperforming SOTA method PointOBB-v2 by 4.10%. Furthermore, when integrated with ORCNN and ReDet architectures, the SSP framework achieves mAP values of 47.86% and 48.50%, respectively. The code is available at https://github.com/antxinyuan/ssp.