Multistage Enhancement Network for Tiny Object Detection in Remote Sensing Images

Tianyang Zhang, Xiangrong Zhang, Xiaoqian Zhu, Guanchun Wang, Xiao Han, Xu Tang, Licheng Jiao

Abstract: With the rapid advances in deep learning techniques, remote sensing object detection (RSOD) has achieved remarkable achievements in recent years. However, tiny object detection remains unsatisfactory and suffers from two main drawbacks: 1) the high sensitivity of IoU for location deviation in tiny objects and 2) the poor-quality feature representations of tiny objects. To address the aforementioned problems, we propose a multistage enhancement network (MENet) that achieves the instance-level and feature-level enhancement of tiny objects from different stages of the detector. Since the IoU-based label assignment drastically deteriorates the positive samples for tiny objects, we first propose a central region (CR)-based label assignment to substitute it in the region proposal network (RPN). The CR label assignment regards the anchors that fall into the CR of ground-truth boxes as positive samples, which provides more positive samples for tiny objects. Then, we design a gated context aggregation (GCA) module that selectively aggregates valuable context information to enhance the feature representation of tiny objects. Additionally, we devise a positive RoI (pRoI) feature generator in the region convolutional neural network (R-CNN) to generate a rich diversity of high-quality pRoI features for tiny objects. We conduct extensive experiments on AI-TOD and SODA-A datasets, and the results demonstrate the effectiveness of our proposed method.