Benchmarks, such as COCO, play a crucial role in object detection. However, existing benchmarks are insufficient in scale variation, and their protocols are inadequate for fair comparison. In this paper, we introduce the Universal-Scale object detection Benchmark (USB). USB has variations in object scales and image domains by incorporating COCO with the recently proposed Waymo Open Dataset and Manga109-s dataset. To enable fair comparison, we propose USB protocols by defining multiple thresholds for training epochs and evaluation image resolutions. By analyzing methods on the proposed benchmark, we designed fast and accurate object detectors called UniverseNets, which surpassed all baselines on USB and achieved state-of-the-art results on existing benchmarks. Specifically, UniverseNets achieved 54.1% AP on COCO test-dev with 20 epochs training, the top result among single-stage detectors on the Waymo Open Dataset Challenge 2020 2D detection, and the first place in the NightOwls Detection Challenge 2020 all objects track. The code is available at https://github.com/shinya7y/UniverseNet .

翻译：基准(如COCO)在物体探测中发挥着关键作用。然而,现有的基准在规模变化方面不够充分,其协议也不足以进行公平的比较。在本文件中,我们采用了通用天体探测基准(USB)。USB将COCO与最近提议的Waymo开放数据集和Manga109-s数据集结合,从而在物体大小和图像域上有所不同。为了能够进行公平的比较,我们提出USB协议,为培训时代和评估图像分辨率规定了多个阈值。通过分析拟议基准的方法,我们设计了称为宇宙网络的快速和准确的物体探测器,该探测器超过了USB的所有基线,并在现有基准上取得了最先进的结果。具体地说,宇宙网络在COCO测试-devd上实现了54.1%的AP,进行了20个小区培训,在Waymo开放数据挑战20202D探测站的单阶段探测器中取得了最高结果,在2020年夜间观测挑战所有物体轨道的第一个位置。该代码可在https://github.com/shinya7/UniverseNet上查阅。