增采样
遥感
计算机科学
目标检测
计算机视觉
人工智能
融合
传感器融合
图像融合
对象(语法)
遥感应用
像素
航空影像
特征提取
合成孔径雷达
图像分割
雷达探测
基于对象
雷达成像
作者
Yongjia Wang,Wangyuan Li,Chao Gao,Xianghua Li,Xiao Yang
标识
DOI:10.1109/jstars.2026.3736719
摘要
Aerial object detection has witnessed remarkable progress, yet detecting tiny objects in remote sensing imagery remains highly challenging due to their extremely limited spatial footprints. Hierarchical feature processing pipelines tend to exacerbate this problem, as their standard spatial downsampling operators discard fragile structural cues, while cross-scale fusion often overlooks the representational inconsistency between shallow details and deep contextual priors. To address these bottlenecks, we propose DeCoF for tiny object detection in aerial imagery via two complementary modules. First, we introduce the detail-retentive downsampling (DRD) module, which performs spatial downsampling through polyphase decomposition followed by detail re-encoding. Equipped with learnable structure-preserving shrinkage and a residual-guided update mechanism, DRD suppresses background clutter while alleviating the distortion of fragile object cues. Second, we present the conflict-aware fusion (CAF) module, which explicitly measures the representational inconsistency between shallow details and deep contextual priors to guide cross-scale fusion. Specifically, CAF quantifies such discrepancies via Kullback-Leibler (KL) divergence, dynamically highlighting ambiguous regions and selectively enhancing complementary contextual priors for more effective multiscale feature aggregation. Extensive experiments on the VisDrone2019 and AI-TOD benchmarks demonstrate the effectiveness and superiority of the proposed DeCoF. Specifically, on the VisDrone2019 benchmark, integrating DeCoF yields absolute improvements of 1.7 points in mAP $_{50}$ and 1.6 points in mAP $_{\text{S}}$ over the pre-trained YOLOv9 baseline, and 2.0 points in mAP $_{50}$ and 1.6 points in mAP $_{\text{S}}$ over the RT-DETR baseline. Furthermore, on the AI-TOD dataset, the RT-DETR-based DeCoF achieves 51.1% in mAP $_{50}$ and 22.1% in mAP $_{\text{S}}$ . These consistent gains across both CNN-based and transformer-based detectors further verify the paradigm-agnostic nature of DeCoF.
科研通智能强力驱动
Strongly Powered by AbleSci AI