mlsanityData to 7 Oct 2026

USB: Universal-Scale Object Detection Benchmark

arXiv 2103.14027 ↗First posted 25 Mar 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

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 and inclusive research, we propose training and evaluation protocols. They have multiple divisions for training epochs and evaluation image resolutions, like weight classes in sports, and compatibility across training protocols, like the backward compatibility of the Universal Serial Bus. Specifically, we request participants to report results with not only higher protocols (longer training) but also lower protocols (shorter training). Using the proposed benchmark and protocols, we conducted extensive experiments using 15 methods and found weaknesses of existing COCO-biased methods. The code is available at https://github.com/shinya7y/UniverseNet .

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 65 of its 106 references that are in the map. First posted on arXiv 25 Mar 2021.

Builds on

65 of 106 references.

References · 65

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  11. 2014Going Deeper with Convolutionscited by 4,231
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
38 more
  1. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  2. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  5. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  6. 2017Deformable Convolutional Networkscited by 1,481
  7. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  8. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  9. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  10. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  11. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  12. 2019Green AIcited by 620
  13. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  14. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  15. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  16. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  17. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  18. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  19. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  20. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 380
  21. 2018Rethinking ImageNet Pre-trainingcited by 376
  22. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  23. 2020A Metric Learning Reality Checkcited by 317
  24. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  25. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  26. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  27. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  28. 2016Speed/accuracy trade-offs for modern convolutional object detectorscited by 198
  29. 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
  30. 2020Probabilistic Anchor Assignment with IoU Prediction for Object Detectioncited by 150
  31. 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
  32. 2017DSSD : Deconvolutional Single Shot Detectorcited by 130
  33. 2021Simple multi-dataset detectioncited by 126
  34. 2017An Analysis of Scale Invariance in Object Detection - SNIPcited by 119
  35. 2020TIDE: A General Toolbox for Identifying Object Detection Errorscited by 113
  36. 2019Towards Universal Object Detection by Domain Attentioncited by 89
  37. 2018Data Augmentation using Random Image Cropping and Patching for Deep CNNscited by 87
  38. 2020Revisiting the Sibling Head in Object Detectorcited by 82

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 2; 2025: 1; 2026: 1.

9 papers.

  1. 2022BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-trainingcited by 33
  2. 2023MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Resultscited by 7
  3. 2023When Multi-Task Learning Meets Partial Supervision: A Computer Vision Reviewcited by 6
  4. 2022Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Surveycited by 3
  5. 2025MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Resultscited by 2
  6. 2023BandRe: Rethinking Band-Pass Filters for Scale-Wise Object Detection Evaluationcited by 1
  7. 2024Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritizationcited by 1
  8. 2024Online Pseudo-Label Unified Object Detection for Multiple Datasets Trainingcited by 0
  9. 2026Telescope: Learnable Hyperbolic Foveation for Ultra-Long-Range Object Detectioncited by 0