mlsanityData to 7 Oct 2026

Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection

arXiv 2207.02541 ↗First posted 6 Jul 2022cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the dense prediction as a united and straightforward form of pseudo-label. Compared to the pseudo-boxes, our Dense Pseudo-Label (DPL) does not involve any post-processing method, thus retaining richer information. We also introduce a region selection technique to highlight the key information while suppressing the noise carried by dense labels. We name our proposed SS-OD algorithm that leverages the DPL as Dense Teacher. On COCO and VOC, Dense Teacher shows superior performance under various settings compared with the pseudo-box-based methods.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 6 Jul 2022.

Builds on

27 of 42 references.

References · 27

  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. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  9. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  10. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  12. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
15 more
  1. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  2. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  3. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  4. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  5. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  6. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  7. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  8. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  9. 2014Learning with Pseudo-Ensemblescited by 241
  10. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
  11. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
  12. 2021Rethinking Pseudo Labels for Semi-Supervised Object Detectioncited by 45
  13. 2021Distilling Object Detectors with Feature Richnesscited by 38
  14. 2021Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Trainingcited by 28
  15. 2020PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppressioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 20; 2024: 11; 2025: 10; 2026: 6.

48 papers.

Sort:

By area:

  1. 2022Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detectioncited by 43
  2. 2023Semi-DETR: Semi-Supervised Object Detection with Detection Transformerscited by 27
  3. 2023Boosting Semi-Supervised Learning by Exploiting All Unlabeled Datacited by 26
  4. 2023SOOD: Towards Semi-Supervised Oriented Object Detectioncited by 19
  5. 2023DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detectioncited by 18
  6. 2023Doubly Robust Self-Trainingcited by 18
  7. 2023Efficient Teacher: Semi-Supervised Object Detection for YOLOv5cited by 17
  8. 2023Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detectioncited by 14
  9. 2023Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detectioncited by 14
  10. 2023MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detectioncited by 13
  11. 2024SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detectioncited by 12
  12. 2023Mixed Pseudo Labels for Semi-Supervised Object Detectioncited by 10
36 more
  1. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
  2. 2023Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detectioncited by 5
  3. 2023Semi-supervised Object Detection: A Survey on Recent Research and Progresscited by 5
  4. 2023Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Imagescited by 4
  5. 2024Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformercited by 4
  6. 2025Semi-Supervised Weed Detection in Vegetable Fields: In-domain and Cross-domain Experimentscited by 4
  7. 2023Pseudo-label Correction and Learning For Semi-Supervised Object Detectioncited by 3
  8. 2025Partial Weakly-Supervised Oriented Object Detectioncited by 3
  9. 2025SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spottingcited by 2
  10. 2025LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detectioncited by 2
  11. 2026EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VRcited by 2
  12. 2023Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detectioncited by 1
  13. 2023Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Imagescited by 1
  14. 2024SSF3D: Strict Semi-Supervised 3D Object Detection with Switching Filtercited by 1
  15. 2024Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volumecited by 1
  16. 2024IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Taskscited by 1
  17. 2024Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teachercited by 1
  18. 2025Pseudo-Labeling Driven Refinement of Benchmark Object Detection Datasets via Analysis of Learning Patternscited by 1
  19. 2025VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detectioncited by 1
  20. 2025GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detectioncited by 1
  21. 2023Online Open-set Semi-supervised Object Detection with Dual Competing Headcited by 0
  22. 2023Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Imagescited by 0
  23. 2023Density-Guided Dense Pseudo Label Selection For Semi-supervised Oriented Object Detectioncited by 0
  24. 2024Skeleton-Guided Sparse Anchors for Rotated Instance Segmentation in Cell Microscopycited by 0
  25. 2024Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learningcited by 0
  26. 2024TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detectioncited by 0
  27. 2024Unbiased Regression Loss for DETRscited by 0
  28. 2024Co-Learning: Towards Semi-Supervised Object Detection with Road-side Camerascited by 0
  29. 2025S2Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detectioncited by 0
  30. 2025Robust and Label-Efficient Deep Waste Detectioncited by 0
  31. 2025SADA: Safe and Adaptive Aggregation of Multiple Black-Box Predictions in Semi-Supervised Learningcited by 0
  32. 2026Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learningcited by 0
  33. 2026Bounding Box Label Propagation for Re-Annotation of Document Layout Analysis Datasetscited by 0
  34. 2026Simple Supervision Is Hard to Beat: A Bitter Lesson from Sparse Target Labels in Domain-Adaptive Object Detectioncited by 0
  35. 2026Towards Sparsely Annotated Open-World Object Detectioncited by 0
  36. 2026Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagerycited by 0