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

arXiv: https://arxiv.org/abs/2203.05983 · HTML: https://mlsanity.com/paper/2203.05983/

## 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 (most cited first, 30 of 31)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation](https://mlsanity.com/paper/1502.02734/) (2015)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [Improving Semantic Segmentation via Video Propagation and Label Relaxation](https://mlsanity.com/paper/1812.01593/) (2018)
- [Single-Shot Refinement Neural Network for Object Detection](https://mlsanity.com/paper/1711.06897/) (2017)
- [Know Your Surroundings: Exploiting Scene Information for Object Tracking](https://mlsanity.com/paper/2003.11014/) (2020)
- [Humble Teachers Teach Better Students for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.10456/) (2021)
- [Uncertainty Aware Semi-Supervised Learning on Graph Data](https://mlsanity.com/paper/2010.12783/) (2020)
- [Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights](https://mlsanity.com/paper/2009.11924/) (2020)
- [SDCNet: Video Prediction Using Spatially-Displaced Convolution](https://mlsanity.com/paper/1811.00684/) (2018)
- [Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces](https://mlsanity.com/paper/2109.00162/) (2021)
- [GAN-generated Faces Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2202.07145/) (2022)
- [Optimizing Video Object Detection via a Scale-Time Lattice](https://mlsanity.com/paper/1804.05472/) (2018)
- [Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos](https://mlsanity.com/paper/1505.05769/) (2015)
- [Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentation](https://mlsanity.com/paper/1803.03778/) (2018)

## Built on by (most cited first, 10 of 10)

- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [Robust COVID-19 Detection in CT Images with CLIP](https://mlsanity.com/paper/2403.08947/) (2024)
- [CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset](https://mlsanity.com/paper/2206.01381/) (2022)
- [Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection](https://mlsanity.com/paper/2305.08069/) (2023)
- [Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformation](https://mlsanity.com/paper/2304.10249/) (2023)
- [Robust Fairness Vision-Language Learning for Medical Image Analysis](https://mlsanity.com/paper/2505.03153/) (2025)
- [Attacking Important Pixels for Anchor-free Detectors](https://mlsanity.com/paper/2301.11457/) (2023)
- [SSVOD: Semi-Supervised Video Object Detection with Sparse Annotations](https://mlsanity.com/paper/2309.01391/) (2023)
- [Object Detection for Autonomous Dozers](https://mlsanity.com/paper/2208.08570/) (2022)
- [Research on Driving Scenario Technology Based on Multimodal Large Lauguage Model Optimization](https://mlsanity.com/paper/2506.02014/) (2025)

## 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.