mlsanityData to 7 Oct 2026

DETRs with Hybrid Matching

arXiv 2207.13080 ↗First posted 26 Jul 2022cs.CVcited by 149

Not on the map. Why?

Abstract (arXiv)

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) to remove duplicate detections. This end-to-end signature is important for the versatility of DETR, and it has been generalized to broader vision tasks. However, we note that there are few queries assigned as positive samples and the one-to-one set matching significantly reduces the training efficacy of positive samples. We propose a simple yet effective method based on a hybrid matching scheme that combines the original one-to-one matching branch with an auxiliary one-to-many matching branch during training. Our hybrid strategy has been shown to significantly improve accuracy. In inference, only the original one-to-one match branch is used, thus maintaining the end-to-end merit and the same inference efficiency of DETR. The method is named H-DETR, and it shows that a wide range of representative DETR methods can be consistently improved across a wide range of visual tasks, including DeformableDETR, PETRv2, PETR, and TransTrack, among others. The code is available at: https://github.com/HDETR

Key facts. Cited by 149 papers in the map (data through 7 Oct 2026). Builds on 79 of its 94 references that are in the map. First posted on arXiv 26 Jul 2022.

Builds on

79 of 94 references.

References · 79

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  8. 2022A ConvNet for the 2020scited by 3,545
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  12. 2015Fast R-CNNcited by 2,930
38 more
  1. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  3. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  4. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  5. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  6. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  7. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  8. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  9. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  12. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  13. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  14. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  15. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  16. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  17. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  18. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  19. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  20. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  21. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  22. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  23. 2021Conditional DETR for Fast Training Convergencecited by 422
  24. 2021Transformer Trackingcited by 412
  25. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  26. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  27. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  28. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  29. 2021Learning Spatio-Temporal Transformer for Visual Trackingcited by 348
  30. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 347
  31. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  32. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  33. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  34. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  35. 2021Group-Free 3D Object Detection via Transformerscited by 215
  36. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  37. 2022Language as Queries for Referring Video Object Segmentationcited by 180
  38. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 11; 2023: 46; 2024: 41; 2025: 30; 2026: 21.

149 papers.

Sort:

By area:

  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  2. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
  3. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  4. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  5. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  6. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  7. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  8. 2023CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matchingcited by 133
  9. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  10. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  11. 2023End-to-End 3D Dense Captioning with Vote2Cap-DETRcited by 77
  12. 2023Dense Distinct Query for End-to-End Object Detectioncited by 76
38 more
  1. 2022DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spottingcited by 74
  2. 2023Cross Modal Transformer: Towards Fast and Robust 3D Object Detectioncited by 68
  3. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  4. 2023Exploring Predicate Visual Context in Detecting Human-Object Interactionscited by 56
  5. 2023ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolutioncited by 52
  6. 2023Rank-DETR for High Quality Object Detectioncited by 49
  7. 2026Ultralytics YOLO26: Unified Real-Time End-to-End Vision Modelscited by 47
  8. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  9. 2023Detection Transformer with Stable Matchingcited by 43
  10. 2023EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understandingcited by 39
  11. 2023Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioningcited by 38
  12. 2022DETRDistill: A Universal Knowledge Distillation Framework for DETR-familiescited by 36
  13. 2023Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETRcited by 36
  14. 2024LW-DETR: A Transformer Replacement to YOLO for Real-Time Detectioncited by 36
  15. 2023V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detectioncited by 34
  16. 2024MS-DETR: Efficient DETR Training with Mixed Supervisioncited by 34
  17. 2022Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningcited by 33
  18. 2022NMS Strikes Backcited by 33
  19. 2024PTQ4SAM: Post-Training Quantization for Segment Anythingcited by 32
  20. 2024Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinementcited by 30
  21. 2024Enhancing Vectorized Map Perception with Historical Rasterized Mapscited by 29
  22. 2024Relation DETR: Exploring Explicit Position Relation Prior for Object Detectioncited by 27
  23. 2025UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interfacecited by 27
  24. 2023Uni3DETR: Unified 3D Detection Transformercited by 26
  25. 2022ConQueR: Query Contrast Voxel-DETR for 3D Object Detectioncited by 21
  26. 2023Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Trackingcited by 20
  27. 2022D3ETR: Decoder Distillation for Detection Transformercited by 17
  28. 2022Enhanced Training of Query-Based Object Detection via Selective Query Recollectioncited by 17
  29. 2023RepViT-SAM: Towards Real-Time Segmenting Anythingcited by 17
  30. 2024On Efficient Variants of Segment Anything Model: A Surveycited by 16
  31. 2024Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Modelscited by 15
  32. 2024Scalable 3D Panoptic Segmentation As Superpoint Graph Clusteringcited by 14
  33. 2024Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detectioncited by 13
  34. 2024Open World Object Detection: A Surveycited by 13
  35. 2024Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Modelscited by 13
  36. 2023S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representationscited by 12
  37. 2024Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detectioncited by 11
  38. 2024A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationshipscited by 11

50 most cited of 149 All 149 (JSON)