Multiscale Gaussian Attention Mechanism for Tiny-Object Detection in Remote Sensing Images

Tiny-object detection is increasingly crucial in fields such as remote sensing, traffic monitoring, and robotics. Inspired by human visual perception, the attention mechanism has become a widely used method for enhancing object detection performance. While existing attention mechanisms have significantly advanced general object detection performance, they often fall short in adapting to the characteristics of tiny-object datasets, including huge object size variations and concentrated distributions. In detail, most current attention mechanisms rely on convolutional or linear layers with fixed receptive fields to compute attention vectors. Some methods attempt to enlarge the receptive fields by using multiscale structures, but they often simply sum feature maps, leading to information interference and increased computational costs. To address these issues, we propose a novel multiscale Gaussian attention mechanism (MGAM). This mechanism integrates multiscale receptive fields with dynamic feature weighting and a Gaussian attention module (GAM), replacing traditional convolutional layers to reduce training and inference overhead. In addition, our mechanism can be easily embedded into various detectors without any hyperparameters. Extensive experiments on six object detection datasets demonstrate the effectiveness and robustness of our method. The code is available at https://github.com/cszzshi/MGAM