Abstract
Targets in remote sensing images are usually small, weakly textured, and easily disturbed by complex backgrounds, challenging high-precision detection with general algorithms. Building on our earlier ESM-YOLO, this work presents ESM-YOLO+ as a lightweight visible infrared fusion network. To enhance detection, ESM-YOLO+ includes two key innovations. (1) A Mask-Enhanced Attention Fusion (MEAF) module fuses features at the pixel level via learnable spatial masks and spatial attention, effectively aligning RGB and infrared features, enhancing small-target representation, and alleviating cross-modal misalignment and scale heterogeneity. (2) Training-time Structural Representation (SR) enhancement provides auxiliary supervision to preserve fine-grained spatial structures during training, boosting feature discriminability without extra inference cost. Extensive experiments on the VEDAI and DroneVehicle datasets validate ESM-YOLO+'s superiority. The model achieves 84.71\% mAP on VEDAI and 74.0\% mAP on DroneVehicle, while greatly reducing model complexity, with 93.6\% fewer parameters and 68.0\% lower GFLOPs than the baseline. These results confirm that ESM-YOLO+ integrates strong performance with practicality for real-time deployment, providing an effective solution for high-performance small-target detection in complex remote sensing scenes.
Abstract (translated)
在遥感图像中，目标通常很小、纹理较弱，并且容易受到复杂背景的干扰，这给一般算法进行高精度检测带来了挑战。在此前的工作 ESM-YOLO 的基础上，我们提出了 ESM-YOLO+，这是一种轻量级的可见光与红外融合网络。为了提升检测效果，ESM-YOLO+ 包含了两项关键创新： 1. **Mask-Enhanced Attention Fusion (MEAF) 模块**：该模块通过可学习的空间掩码和空间注意力机制在像素级别上融合特征，有效地对齐 RGB 和红外特性，增强小目标的表现，并缓解跨模态错配及尺度异质性问题。 2. **训练时间结构表示（SR）增强**：这种辅助监督提供了在训练期间保持精细的时空结构的方法，在不增加推理成本的情况下提高特征判别能力。 在 VEDAI 和 DroneVehicle 数据集上的广泛实验验证了 ESM-YOLO+ 的优越性能。该模型在 VEDAI 上实现了 84.71% mAP，而在 DroneVehicle 上达到了 74.0% mAP，并且极大地减少了模型复杂度，参数量比基线少了93.6%，GFLOPs（十亿次浮点运算）则低了68.0%。这些结果表明 ESM-YOLO+ 结合了强大的性能和实际应用性，可以实现实时部署，为在复杂的遥感场景中进行高性能小目标检测提供了有效的解决方案。
URL
https://arxiv.org/abs/2603.06925
