Current mainstream object detection methods for large aerial images usually divide large images into patches and then exhaustively detect the objects of interest on all patches, no matter whether there exist objects or not. This paradigm, although effective, is inefficient because the detectors have to go through all patches, severely hindering the inference speed. This paper presents an Objectness Activation Network (OAN) to help detectors focus on fewer patches but achieve more efficient inference and more accurate results, enabling a simple and effective solution to object detection in large images. In brief, OAN is a light fully-convolutional network for judging whether each patch contains objects or not, which can be easily integrated into many object detectors and jointly trained with them end-to-end. We extensively evaluate our OAN with five advanced detectors. Using OAN, all five detectors acquire more than 30.0% speed-up on three large-scale aerial image datasets, meanwhile with consistent accuracy improvements. On extremely large Gaofen-2 images (29200$\times$27620 pixels), our OAN improves the detection speed by 70.5%. Moreover, we extend our OAN to driving-scene object detection and 4K video object detection, boosting the detection speed by 112.1% and 75.0%, respectively, without sacrificing the accuracy. Code is available at https://github.com/Ranchosky/OAN.

翻译：当前主流的大型遥感图像目标检测方法通常将大图划分为图像块，然后对所有图像块进行穷举式目标检测，无论其中是否存在目标。这种范式虽然有效，但效率低下，因为检测器必须遍历所有图像块，严重制约了推理速度。本文提出了一种目标激活网络（Objectness Activation Network, OAN），帮助检测器聚焦于更少的图像块，同时实现更高效的推理和更精确的结果，为大图像目标检测提供了一种简单有效的解决方案。简言之，OAN是一个轻量级全卷积网络，用于判断每个图像块是否包含目标，可轻松集成到多种目标检测器中，并与它们进行端到端联合训练。我们在五个先进检测器上对OAN进行了全面评估。使用OAN后，所有五个检测器在三个大规模遥感图像数据集上的速度提升均超过30.0%，同时保持一致的精度提升。在超大尺寸高景二号卫星图像（29200×27620像素）上，我们的OAN将检测速度提升了70.5%。此外，我们将OAN扩展到驾驶场景目标检测和4K视频目标检测，在未牺牲精度的前提下，分别将检测速度提升了112.1%和75.0%。代码已开源在https://github.com/Ranchosky/OAN。