# Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detection Source: [Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detection]() Collection index: [llms.txt]() Data updated: 2026-06-06T05:00:04.315Z Authors: Xinyuan Liu, Hang Xu, Zirui Chen, Yike Ma, Chenggang Yan, Feng Dai Published: 2025-06-12T11:44:34.000Z ## Abstract Given its ability to reduce annotation costs, weakly supervised learning based on single-point annotations has emerged as a research focus in oriented object detection. Compared with the classical teacher-student paradigm, the simple model paradigm (e.g., PointOBB-v2) can substantially further reduce resources required for training while ensuring strong performance. The latter exhibits greater potential for low-cost training, yet such methods still face challenges of insufficient sample assignment and poor pseudo-label quality. In this paper, we propose a training-efficient framework named SSP, which synergizes rule-driven prior injection and data-driven label purification. Specifically, SSP introduces two designs: (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 converts them into pseudo-boxes for supervising detectors. Experiments on DOTA-v1.0 and other datasets demonstrate SSP's superiority: it achieves +6.73% mAP improvement compared with the baseline, while requiring only 2 h of training time and 6 GB of GPU memory. Furthermore, when SSP is integrated with stronger detector, the mAP can reach 50.81%. The code is available at https://github.com/antxinyuan/ssp. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Oriented Object Detection on RSAR](): Oriented Object Detection; RSAR; AP50: 31.16. - [Oriented Object Detection on DOTA v2.0](): Oriented Object Detection; DOTA v2.0; AP50: 29.02. - [Oriented Object Detection on DOTA v1.5](): Oriented Object Detection; DOTA v1.5; AP@50: 35.93. - [Oriented Object Detection on DOTA v1.0](): Oriented Object Detection; DOTA v1.0; AP50: 50.81. ## Original sources and implementation [Original paper]() [PDF]()