mlsanityData to 14 Oct 2026

PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems

arXiv 2203.05983 ↗First posted 11 Mar 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled. To propagate information from the labeled objects to the unlabeled ones, pseudo-labels for unlabeled objects must be generated. Although pseudo-labels have proven to improve the performance of semi-supervised object detection significantly, the applications of image-based methods to video frames result in numerous miss or false detections using such generated pseudo-labels. In this paper, we propose a new approach, PseudoProp, to generate robust pseudo-labels by leveraging motion continuity in video frames. Specifically, PseudoProp uses a novel bidirectional pseudo-label propagation approach to compensate for misdetection. A feature-based fusion technique is also used to suppress inference noise. Extensive experiments on the large-scale Cityscapes dataset demonstrate that our method outperforms the state-of-the-art semi-supervised object detection methods by 7.4% on mAP75.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 11 Mar 2022.

Builds on

31 of 44 references.

References · 31

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  8. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  9. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  10. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  11. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 403
  12. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 382
19 more
  1. 2019Tracking without bells and whistlescited by 382
  2. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  3. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 336
  4. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  5. 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
  6. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  7. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  8. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  9. 2020Know Your Surroundings: Exploiting Scene Information for Object Trackingcited by 119
  10. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 116
  11. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  12. 2020Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlightscited by 59
  13. 2018SDCNet: Video Prediction Using Spatially-Displaced Convolutioncited by 50
  14. 2021Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Facescited by 48
  15. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 30
  16. 2018Optimizing Video Object Detection via a Scale-Time Latticecited by 25
  17. 2015Watch and Learn: Semi-Supervised Learning of Object Detectors from Videoscited by 17
  18. 2018Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentationcited by 10
  19. 2021Multi-Object Tracking with Hallucinated and Unlabeled Videoscited by 6

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 2; 2025: 2.

10 papers.

  1. 2024Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Surveycited by 12
  2. 2024Robust COVID-19 Detection in CT Images with CLIPcited by 12
  3. 2022CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Datasetcited by 7
  4. 2023Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detectioncited by 7
  5. 2023Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformationcited by 6
  6. 2025Robust Fairness Vision-Language Learning for Medical Image Analysiscited by 4
  7. 2023Attacking Important Pixels for Anchor-free Detectorscited by 3
  8. 2023SSVOD: Semi-Supervised Video Object Detection with Sparse Annotationscited by 2
  9. 2022Object Detection for Autonomous Dozerscited by 1
  10. 2025Research on Driving Scenario Technology Based on Multimodal Large Lauguage Model Optimizationcited by 0