LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
This addresses sparse annotation challenges in remote sensing object detection, which is an incremental improvement over existing pseudo-labeling methods.
The paper tackles the problem of object detection in remote sensing images with sparse annotations by introducing an LLM-assisted semantic guidance framework that generates high-confidence pseudo-labels. The method achieves significant performance improvements on DOTA and HRSC2016 datasets compared to existing single-stage detector-based frameworks.
Sparse annotation in remote sensing object detection poses significant challenges due to dense object distributions and category imbalances. Although existing Dense Pseudo-Label methods have demonstrated substantial potential in pseudo-labeling tasks, they remain constrained by selection ambiguities and inconsistencies in confidence estimation.In this paper, we introduce an LLM-assisted semantic guidance framework tailored for sparsely annotated remote sensing object detection, exploiting the advanced semantic reasoning capabilities of large language models (LLMs) to distill high-confidence pseudo-labels.By integrating LLM-generated semantic priors, we propose a Class-Aware Dense Pseudo-Label Assignment mechanism that adaptively assigns pseudo-labels for both unlabeled and sparsely labeled data, ensuring robust supervision across varying data distributions. Additionally, we develop an Adaptive Hard-Negative Reweighting Module to stabilize the supervised learning branch by mitigating the influence of confounding background information. Extensive experiments on DOTA and HRSC2016 demonstrate that the proposed method outperforms existing single-stage detector-based frameworks, significantly improving detection performance under sparse annotations.