With the rise of deep convolutional neural networks, object detection has achieved prominent advances in past years. However, such prosperity could not camouflage the unsatisfactory situation of Small Object Detection (SOD), one of the notoriously challenging tasks in computer vision, owing to the poor visual appearance and noisy representation caused by the intrinsic structure of small targets. In addition, large-scale dataset for benchmarking small object detection methods remains a bottleneck. In this paper, we first conduct a thorough review of small object detection. Then, to catalyze the development of SOD, we construct two large-scale Small Object Detection dAtasets (SODA), SODA-D and SODA-A, which focus on the Driving and Aerial scenarios respectively. SODA-D includes 24828 high-quality traffic images and 278433 instances of nine categories. For SODA-A, we harvest 2513 high resolution aerial images and annotate 872069 instances over nine classes. The proposed datasets, as we know, are the first-ever attempt to large-scale benchmarks with a vast collection of exhaustively annotated instances tailored for multi-category SOD. Finally, we evaluate the performance of mainstream methods on SODA. We expect the released benchmarks could facilitate the development of SOD and spawn more breakthroughs in this field. Datasets and codes are available at: \url{https://shaunyuan22.github.io/SODA}.
翻译:随着深度卷积神经网络的兴起,目标检测在过去几年中取得了重大进展。然而,这样的繁荣无法掩盖小目标检测(SOD)的不理想情况,SOD是计算机视觉中一项极具挑战性的任务之一,由于小目标固有的结构特征导致其外观不佳且噪声大。此外,用于基准测试小目标检测方法的大规模数据集仍然是一个瓶颈。在本文中,我们首先对小目标检测进行了全面的回顾。然后,为了促进SOD的发展,我们构建了两个大规模的小目标检测数据集(SODA),分别是SODA-D和SODA-A,它们分别专注于驾驶和航空场景。SODA-D包括24828个高质量的交通图像,共278433个九类目标实例。对于SODA-A,我们收集了2513个高分辨率的航空图像,并标注了872069个来自九个类别的实例。据我们所知,提出的数据集是首次尝试针对多类别SOD量身定制的大规模基准测试,其中包含大量详细注释的实例。最后,我们评估了主流方法在SODA上的性能。我们希望发布的基准测试可以促进SOD的发展,并在该领域孕育更多突破性进展。数据集和代码可在以下链接处获得:\url {https://shaunyuan22.github.io/SODA}。