mlsanityData to 7 Oct 2026

LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection

arXiv 2406.03459 ↗First posted 5 Jun 2024cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages recent advanced techniques, such as training-effective techniques, e.g., improved loss and pretraining, and interleaved window and global attentions for reducing the ViT encoder complexity. We improve the ViT encoder by aggregating multi-level feature maps, and the intermediate and final feature maps in the ViT encoder, forming richer feature maps, and introduce window-major feature map organization for improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time detectors, e.g., YOLO and its variants, on COCO and other benchmark datasets. Code and models are available at (https://github.com/Atten4Vis/LW-DETR).

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 60 of its 73 references that are in the map. First posted on arXiv 5 Jun 2024.

Builds on

60 of 73 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2016Densely Connected Convolutional Networkscited by 6,691
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  11. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  12. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
38 more
  1. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  3. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  4. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  5. 2022Planning-oriented Autonomous Drivingcited by 1,068
  6. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  7. 2021Scaling Vision Transformerscited by 993
  8. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  9. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  10. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  11. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  12. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  13. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  14. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  15. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  16. 2021Conditional DETR for Fast Training Convergencecited by 422
  17. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  18. 2019Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challengescited by 313
  19. 2022Context Autoencoder for Self-Supervised Representation Learningcited by 297
  20. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  21. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  22. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  23. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  24. 2022DETRs with Hybrid Matchingcited by 149
  25. 2021Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentationcited by 133
  26. 2021Benchmarking Detection Transfer Learning with Vision Transformerscited by 130
  27. 2017Learning non-maximum suppressioncited by 112
  28. 2019GS3D: An Efficient 3D Object Detection Framework for Autonomous Drivingcited by 106
  29. 2021Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsitycited by 98
  30. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 96
  31. 2022AdaMixer: A Fast-Converging Query-Based Object Detectorcited by 78
  32. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  33. 2023FasterViT: Fast Vision Transformers with Hierarchical Attentioncited by 65
  34. 2023YOLOv6 v3.0: A Full-Scale Reloadingcited by 58
  35. 2023Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanismcited by 51
  36. 2023Detection Transformer with Stable Matchingcited by 43
  37. 2023Less is More: Focus Attention for Efficient DETRcited by 38
  38. 2022DETRDistill: A Universal Knowledge Distillation Framework for DETR-familiescited by 36

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 12; 2026: 18.

36 papers.

Sort:

By area:

  1. 2024DINO-X: A Unified Vision Model for Open-World Object Detection and Understandingcited by 85
  2. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  3. 2025RF-DETR: Neural Architecture Search for Real-Time Detection Transformerscited by 70
  4. 2025Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Modelscited by 20
  5. 2024LaMI-DETR: Open-Vocabulary Detection with Language Model Instructioncited by 19
  6. 2025Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detectioncited by 6
  7. 2025FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimationcited by 4
  8. 2024OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformercited by 3
  9. 2025Create Anything Anywhere: Layout-Controllable Personalized Diffusion Model for Multiple Subjectscited by 3
  10. 2026EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillationcited by 2
  11. 2024PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slicescited by 1
  12. 2024Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Expertscited by 1
24 more
  1. 2025DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypointscited by 1
  2. 2025DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detectioncited by 1
  3. 2025FruitProm: Probabilistic Maturity Estimation and Detection of Fruits and Vegetablescited by 1
  4. 2025LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detectioncited by 1
  5. 2026RiO-DETR: DETR for Real-time Oriented Object Detectioncited by 1
  6. 2026WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objectscited by 1
  7. 2026RT-SDGOD: Real-Time Single-Domain Generalized Object Detectioncited by 1
  8. 2025JDATT: A Joint Distillation Framework for Atmospheric Turbulence Mitigation and Target Detectioncited by 0
  9. 2025A Distributed Framework for Privacy-Enhanced Vision Transformers on the Edgecited by 0
  10. 2025Comparing Object Detection Models for Electrical Substation Component Mappingcited by 0
  11. 2026FlyPose: Towards Robust Human Pose Estimation From Aerial Viewscited by 0
  12. 2026Multimodal Urban Tree Detection from Satellite and Street-Level Imagery via Annotation-Efficient Deep Learning Strategiescited by 0
  13. 2026SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detectioncited by 0
  14. 2026Echo-α: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretationcited by 0
  15. 2026Real-Time Source-Free Object Detectioncited by 0
  16. 2026Enabling Fully Integer-Only Inference for Lightweight Detection Transformerscited by 0
  17. 2026ScratchSim: A Procedural Synthetic Data Pipeline for Surface Scratch Detectioncited by 0
  18. 2026Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformerscited by 0
  19. 2026LocAnyMed: Vision-Language Grounding for Multimodal Medical Imagescited by 0
  20. 2026TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformerscited by 0
  21. 2026DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detectioncited by 0
  22. 2026HOIBlender: Blending Lightweight Detection with Vision-Language Priors for Efficient Human-Object Interaction Detectioncited by 0
  23. 2026GTR: Gated Token Recurrence for Efficient Dense Predictioncited by 0
  24. 2026Curating Synthetic Data for Task-Specific Visual Perceptioncited by 0