mlsanityData to 7 Oct 2026

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

arXiv 2103.16368 ↗First posted 29 Mar 2021cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models. Previous semi-supervised methods based on pseudo labels are severely degenerated by noise and prone to overfit to noisy labels, thus are deficient in learning different unlabeled knowledge well. To address this issue, we propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection. We comprehensively consider divergent types of unlabeled images according to their difficulty levels, utilize them in different phases and ensemble models from different phases together to generate ultimate results. Image uncertainty guided easy data selection and region uncertainty guided RoI Re-weighting are involved in multi-phase learning and enable the detector to concentrate on more certain knowledge. Through extensive experiments on PASCAL VOC and MS COCO, we demonstrate that our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin, more than 3% on VOC and 2% on COCO.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 40 of its 56 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

40 of 56 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Fast R-CNNcited by 2,930
  9. 2018YOLOv3: An Incremental Improvementcited by 2,652
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  11. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  12. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
28 more
  1. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  2. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  3. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  4. 2017A Closer Look at Memorization in Deep Networkscited by 936
  5. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  6. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  7. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
  8. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  9. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  10. 2020Rethinking Pre-training and Self-trainingcited by 352
  11. 2015Weakly Supervised Deep Detection Networkscited by 183
  12. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  13. 2019Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentationcited by 138
  14. 2017Data Distillation: Towards Omni-Supervised Learningcited by 126
  15. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  16. 2020Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Trainingcited by 103
  17. 2019Deep Co-Training for Semi-Supervised Image Segmentationcited by 58
  18. 2020Proposal Learning for Semi-Supervised Object Detectioncited by 55
  19. 2018Universal Semi-Supervised Semantic Segmentationcited by 50
  20. 2016Weakly Supervised Cascaded Convolutional Networkscited by 47
  21. 2019Min-Entropy Latent Model for Weakly Supervised Object Detectioncited by 45
  22. 2020Interpolation-based semi-supervised learning for object detectioncited by 40
  23. 2014LSDA: Large Scale Detection Through Adaptationcited by 32
  24. 2018Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detectioncited by 32
  25. 2018Zigzag Learning for Weakly Supervised Object Detectioncited by 24
  26. 2018Soft Sampling for Robust Object Detectioncited by 22
  27. 2019Weighted boxes fusion: Ensembling boxes from different object detection modelscited by 20
  28. 2018Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteriacited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 15; 2023: 14; 2024: 9; 2025: 4; 2026: 2.

48 papers.

Sort:

By area:

  1. 2022Class-Aware Contrastive Semi-Supervised Learningcited by 62
  2. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  3. 2021Rethinking Pseudo Labels for Semi-Supervised Object Detectioncited by 45
  4. 2022Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detectioncited by 43
  5. 2023Active Teacher for Semi-Supervised Object Detectioncited by 43
  6. 2022Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margincited by 32
  7. 2022Dense Learning based Semi-Supervised Object Detectioncited by 32
  8. 2023Teacher-Student Architecture for Knowledge Distillation: A Surveycited by 26
  9. 2023Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detectioncited by 24
  10. 2022Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detectioncited by 23
  11. 2022Teacher-Student Architecture for Knowledge Learning: A Surveycited by 23
  12. 2024Adaptive Bounding Box Uncertainties via Two-Step Conformal Predictioncited by 23
36 more
  1. 2021MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detectioncited by 21
  2. 2022Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?cited by 21
  3. 2023Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimationcited by 19
  4. 2021Combating Noise: Semi-supervised Learning by Region Uncertainty Quantificationcited by 18
  5. 2022Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentationcited by 17
  6. 2022Scale-Equivalent Distillation for Semi-Supervised Object Detectioncited by 15
  7. 2024CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Object Detectioncited by 12
  8. 2025UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Networkcited by 11
  9. 2023Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Modulecited by 10
  10. 2022Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparisoncited by 8
  11. 2023Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstructioncited by 8
  12. 2023Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertaintycited by 7
  13. 2024ACTRESS: Active Retraining for Semi-supervised Visual Groundingcited by 7
  14. 2022CrossRectify: Leveraging Disagreement for Semi-supervised Object Detectioncited by 6
  15. 2022S4OD: Semi-Supervised learning for Single-Stage Object Detectioncited by 6
  16. 2022Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertaintycited by 5
  17. 2023Semi-supervised Object Detection: A Survey on Recent Research and Progresscited by 5
  18. 2023Balanced Classification: A Unified Framework for Long-Tailed Object Detectioncited by 5
  19. 2021Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detectioncited by 2
  20. 2023Semi-Supervised and Long-Tailed Object Detection with CascadeMatchcited by 2
  21. 2024Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimationcited by 2
  22. 2024On-the-Fly Point Annotation for Fast Medical Video Labelingcited by 2
  23. 2024S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Trackingcited by 2
  24. 20253DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentationcited by 2
  25. 2023Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Imagescited by 1
  26. 2023Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labelscited by 1
  27. 2025UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extractioncited by 1
  28. 2026DExTeR: Weakly Semi-Supervised Object Detection with Class and Instance Experts for Medical Imagingcited by 1
  29. 2026Semi-supervised Source Detection in Astronomical Images: New Benchmark and Strong Baselinecited by 1
  30. 2022Semi-supervised object detection based on single-stage detector for thighbone fracture localizationcited by 0
  31. 2023Weakly Supervised Point Clouds Transformer for 3D Object Detectioncited by 0
  32. 2023Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Imagescited by 0
  33. 2024Collaboration of Teachers for Semi-supervised Object Detectioncited by 0
  34. 2024Augmenting Offline RL with Unlabeled Datacited by 0
  35. 2024Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detectioncited by 0
  36. 2025Dual Guidance Semi-Supervised Action Detectioncited by 0