Foreground Attention Loss and Attention-Guided Convolution for Remote Sensing Object Detection

作者：Zilong Wang, Hongxian Tian, Wei Yang, Zishan Xu, Wei Chen, Yunyue Elita Li, Tingting Xu, Jueting Liu, Zehua Wang · 发表于：IEEE Sensors Journal · 年份：2025 · DOI：10.1109/jsen.2025.3624139 · 被引用次数：3 · 研究领域：Infrared Target Detection Methodologies、Remote-Sensing Image Classification、Advanced Image Fusion Techniques

Remote sensing (RS) imagery contains vast backgrounds and densely packed, rotated small objects. One-stage rotated detectors therefore allocate most convolutional samples to background because they lack an explicit foreground discovery step. We close this gap with a lightweight discover→focus pipeline composed of two modules. First, a Foreground Attention Loss (FAL) supervises the classifier’s foreground heatmap by matching it to a rotated target–density map rendered from OBB annotations, giving the detector an explicit notion of “where the objects are.” Second, AGConv computes closed-form semantic–geometric dual offsets by fusing the learned foreground attention with anchor geometry, thereby concentrating sampling in salient regions while suppressing clutter without an extra offset-conv branch. This preserves one-stage efficiency while approximating the proposal-guided foreground extraction of two-stage detectors. Under identical ResNet–50+FPN settings, our single-stage detector attains 76.48% mAP on DOTA-v1.0, 68.65% on DOTA-v1.5, 67.2% on DIOR–R, and 97.28% (VOC12) / 90.82% (VOC07) on HRSC2016, with negligible parameter and latency overhead—demonstrating a strong accuracy–efficiency trade-off for complex RS scenes with dense, rotated targets.