mlsanityData to 7 Oct 2026

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

arXiv 2106.04550 ↗First posted 8 Jun 2021cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method that pretrains the entire object detection network, including the object localization and embedding components. During pretraining, DETReg predicts object localizations to match the localizations from an unsupervised region proposal generator and simultaneously aligns the corresponding feature embeddings with embeddings from a self-supervised image encoder. We implement DETReg using the DETR family of detectors and show that it improves over competitive baselines when finetuned on COCO, PASCAL VOC, and Airbus Ship benchmarks. In low-data regimes DETReg achieves improved performance, e.g., when training with only 1% of the labels and in the few-shot learning settings.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). Builds on 54 of its 82 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

54 of 82 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2015Fast R-CNNcited by 2,930
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  12. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
38 more
  1. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  2. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  3. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  4. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  5. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  6. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  7. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  8. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  9. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  10. 2019Contrastive Multiview Codingcited by 1,297
  11. 2016Colorful Image Colorizationcited by 1,113
  12. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  13. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  14. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  15. 2017Focal Loss for Dense Object Detectioncited by 749
  16. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  17. 2018Rethinking ImageNet Pre-trainingcited by 376
  18. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  19. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  20. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  21. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  22. 2020What Should Not Be Contrastive in Contrastive Learningcited by 224
  23. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  24. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  25. 2019Scaling and Benchmarking Self-Supervised Visual Representation Learningcited by 201
  26. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  27. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  28. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  29. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  30. 2021Instance Localization for Self-supervised Detection Pretrainingcited by 99
  31. 2021Region Similarity Representation Learningcited by 96
  32. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  33. 2018RepMet: Representative-based metric learning for classification and one-shot object detectioncited by 85
  34. 2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 81
  35. 2018LSTD: A Low-Shot Transfer Detector for Object Detectioncited by 77
  36. 2020Learning Representations by Predicting Bags of Visual Wordscited by 73
  37. 2021Spatially Consistent Representation Learningcited by 64
  38. 2021Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitationcited by 44

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 19; 2023: 23; 2024: 19; 2025: 5; 2026: 4.

76 papers.

Sort:

  1. 2022Visual Prompting via Image Inpaintingcited by 248
  2. 2023A Cookbook of Self-Supervised Learningcited by 248
  3. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
  4. 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
  5. 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
  6. 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Reviewcited by 72
  7. 2023MobileSAMv2: Faster Segment Anything to Everythingcited by 41
  8. 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
  9. 2022Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detectioncited by 33
  10. 2022Continual Object Detection: A review of definitions, strategies, and challengescited by 25
  11. 2023Object Detection with Transformers: A Reviewcited by 22
  12. 2022Proper Reuse of Image Classification Features Improves Object Detectioncited by 20
38 more
  1. 2022FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-trainingcited by 20
  2. 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
  3. 2023MOST: Multiple Object localization with Self-supervised Transformers for object discoverycited by 17
  4. 2024CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformerscited by 16
  5. 2022Object Detection in Autonomous Vehicles: Status and Open Challengescited by 14
  6. 2023AlignDet: Aligning Pre-training and Fine-tuning in Object Detectioncited by 14
  7. 2024DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentationcited by 13
  8. 2024Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenescited by 13
  9. 2023Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Promptcited by 11
  10. 2024DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detectioncited by 11
  11. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  12. 2022Dynamic Curriculum Learning for Great Ape Detection in the Wildcited by 10
  13. 2022Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectorscited by 10
  14. 2023IMProv: Inpainting-based Multimodal Prompting for Computer Vision Taskscited by 10
  15. 2023Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervisioncited by 8
  16. 2024LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-trainingcited by 8
  17. 2022Scaling Novel Object Detection with Weakly Supervised Detection Transformerscited by 7
  18. 2023Siamese DETRcited by 7
  19. 2023SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentationcited by 7
  20. 2023Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentationcited by 7
  21. 2021A Survey of Deep Learning for Low-Shot Object Detectioncited by 6
  22. 2023Unsupervised Recognition of Unknown Objects for Open-World Object Detectioncited by 6
  23. 2024Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environmentscited by 6
  24. 2025Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detectioncited by 6
  25. 2022DATA: Domain-Aware and Task-Aware Self-supervised Learningcited by 5
  26. 2022Refine and Represent: Region-to-Object Representation Learningcited by 5
  27. 2023Language-aware Multiple Datasets Detection Pretraining for DETRscited by 5
  28. 2023Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognitioncited by 5
  29. 2023Revisiting DETR Pre-training for Object Detectioncited by 5
  30. 2024MutDet: Mutually Optimizing Pre-training for Remote Sensing Object Detectioncited by 5
  31. 2024BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairmentscited by 5
  32. 2021Semi-weakly Supervised Contrastive Representation Learning for Retinal Fundus Imagescited by 4
  33. 2021ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignmentcited by 4
  34. 2022Few-shot Object Detection with Refined Contrastive Learningcited by 4
  35. 2024Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentationcited by 4
  36. 2024ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videoscited by 4
  37. 2024Physics-Guided Detector for SAR Airplanescited by 4
  38. 2022A Study on Self-Supervised Object Detection Pretrainingcited by 3

50 most cited of 76 All 76 (JSON)