mlsanityData to 7 Oct 2026

RTMDet: An Empirical Study of Designing Real-Time Object Detectors

arXiv 2212.07784 ↗First posted 14 Dec 2022cs.CVcited by 192

Not on the map. Why?

Abstract (arXiv)

In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more efficient model architecture, we explore an architecture that has compatible capacities in the backbone and neck, constructed by a basic building block that consists of large-kernel depth-wise convolutions. We further introduce soft labels when calculating matching costs in the dynamic label assignment to improve accuracy. Together with better training techniques, the resulting object detector, named RTMDet, achieves 52.8% AP on COCO with 300+ FPS on an NVIDIA 3090 GPU, outperforming the current mainstream industrial detectors. RTMDet achieves the best parameter-accuracy trade-off with tiny/small/medium/large/extra-large model sizes for various application scenarios, and obtains new state-of-the-art performance on real-time instance segmentation and rotated object detection. We hope the experimental results can provide new insights into designing versatile real-time object detectors for many object recognition tasks. Code and models are released at https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet.

Key facts. Cited by 192 papers in the map (data through 7 Oct 2026). Builds on 83 of its 101 references that are in the map. First posted on arXiv 14 Dec 2022.

Builds on

83 of 101 references.

References · 83

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  9. 2017Mask R-CNNcited by 7,259
  10. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  11. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  12. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
38 more
  1. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  4. 2015Fast R-CNNcited by 2,930
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  6. 2018YOLOv3: An Incremental Improvementcited by 2,652
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  10. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2018Group Normalizationcited by 1,514
  13. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  14. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  15. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  16. 2019Objects as Pointscited by 1,172
  17. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  18. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  19. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  20. 2018Path Aggregation Network for Instance Segmentationcited by 796
  21. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  22. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  23. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  24. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  25. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  26. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  27. 2019YOLACT: Real-time Instance Segmentationcited by 441
  28. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  29. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  30. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  31. 2020Conditional Convolutions for Instance Segmentationcited by 314
  32. 2017Dilated Residual Networkscited by 293
  33. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  34. 2019SOLO: Segmenting Objects by Locationscited by 289
  35. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  36. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  37. 2021Oriented R-CNN for Object Detectioncited by 230
  38. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218

50 most cited of 83 All 83 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 26; 2024: 66; 2025: 58; 2026: 42.

192 papers.

Sort:

By area:

  1. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  2. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  3. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  4. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  5. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  6. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  7. 2024MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretrainingcited by 66
  8. 2024Poly Kernel Inception Network for Remote Sensing Detectioncited by 52
  9. 2023CrossKD: Cross-Head Knowledge Distillation for Object Detectioncited by 50
  10. 2024LSKNet: A Foundation Lightweight Backbone for Remote Sensingcited by 44
  11. 2024LW-DETR: A Transformer Replacement to YOLO for Real-Time Detectioncited by 36
  12. 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
38 more
  1. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  2. 2024Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computationcited by 29
  3. 2023Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervisioncited by 21
  4. 2024The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noisecited by 18
  5. 2024RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimationcited by 18
  6. 2023MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detectioncited by 17
  7. 2024CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgerycited by 16
  8. 2024ESOD: Efficient Small Object Detection on High-Resolution Imagescited by 15
  9. 2024HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenescited by 15
  10. 2023Responsible Task Automation: Empowering Large Language Models as Responsible Task Automatorscited by 14
  11. 2025Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detectioncited by 14
  12. 2025Object Detection with Multimodal Large Vision-Language Models: An In-depth Reviewcited by 14
  13. 2024GRA: Detecting Oriented Objects through Group-wise Rotating and Attentioncited by 13
  14. 2023Spatial Transform Decoupling for Oriented Object Detectioncited by 12
  15. 2024SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detectioncited by 12
  16. 2025Image Quality Assessment: From Human to Machine Preferencecited by 12
  17. 2025HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debuggingcited by 11
  18. 2023Mixed Pseudo Labels for Semi-Supervised Object Detectioncited by 10
  19. 2023Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformercited by 9
  20. 2024RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perceptioncited by 9
  21. 2024Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detectioncited by 9
  22. 2025OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Imagescited by 9
  23. 2025UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mappingcited by 8
  24. 2025EagleVision: Object-level Attribute Multimodal LLM for Remote Sensingcited by 8
  25. 2025M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detectioncited by 8
  26. 2024Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesiscited by 7
  27. 2025Segment Anything, Even Occludedcited by 7
  28. 2025AIM 2025 Rip Current Segmentation (RipSeg) Challenge Reportcited by 7
  29. 2023Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detectioncited by 6
  30. 2024CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Modelscited by 6
  31. 2025Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challengecited by 6
  32. 2026YOLO26: An Analysis of NMS-Free End to End Framework for Real-Time Object Detectioncited by 6
  33. 2023YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systemscited by 5
  34. 2023UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detectioncited by 5
  35. 2024MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstructioncited by 5
  36. 2024SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Imagescited by 5
  37. 2024ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagerycited by 5
  38. 2024Fractal Calibration for long-tailed object detectioncited by 5

50 most cited of 192 All 192 (JSON)