Guided Attention Network for Object Detection and Counting on Drones
This work addresses object detection and counting for drone-based applications, representing an incremental improvement with novel attention modules.
The paper tackles object detection and counting in drone scenes with small objects and cluttered backgrounds by proposing a Guided Attention Network (GANet), achieving state-of-the-art performance on benchmarks like UAVDT, CARPK, and PUCPR+.
Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background. In this paper, we propose a new Guided Attention Network (GANet) to deal with both object detection and counting tasks based on the feature pyramid. Different from the previous methods relying on unsupervised attention modules, we fuse different scales of feature maps by using the proposed weakly-supervised Background Attention (BA) between the background and objects for more semantic feature representation. Then, the Foreground Attention (FA) module is developed to consider both global and local appearance of the object to facilitate accurate localization. Moreover, the new data argumentation strategy is designed to train a robust model in various complex scenes. Extensive experiments on three challenging benchmarks (i.e., UAVDT, CARPK and PUCPR+) show the state-of-the-art detection and counting performance of the proposed method compared with existing methods.