Context-Enhanced Detector For Building Detection From Remote Sensing Images
This addresses building detection for remote sensing applications, but it is incremental as it builds on existing detection methods with novel modules.
The paper tackled the problem of high-accuracy building detection from remote sensing images by proposing a Context-Enhanced Detector (CEDet) with modules for contextual information extraction, achieving state-of-the-art performance on benchmarks like CNBuilding-9P, CNBuilding-23P, and SpaceNet.
The field of building detection from remote sensing images has made significant progress, but faces challenges in achieving high-accuracy detection due to the diversity in building appearances and the complexity of vast scenes. To address these challenges, we propose a novel approach called Context-Enhanced Detector (CEDet). Our approach utilizes a three-stage cascade structure to enhance the extraction of contextual information and improve building detection accuracy. Specifically, we introduce two modules: the Semantic Guided Contextual Mining (SGCM) module, which aggregates multi-scale contexts and incorporates an attention mechanism to capture long-range interactions, and the Instance Context Mining Module (ICMM), which captures instance-level relationship context by constructing a spatial relationship graph and aggregating instance features. Additionally, we introduce a semantic segmentation loss based on pseudo-masks to guide contextual information extraction. Our method achieves state-of-the-art performance on three building detection benchmarks, including CNBuilding-9P, CNBuilding-23P, and SpaceNet.