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 .
View on arXiv