# Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training

arXiv: https://arxiv.org/abs/2107.05031 · HTML: https://mlsanity.com/paper/2107.05031/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 53 references that are in the map.
- First posted on arXiv 11 Jul 2021.

## Builds on (most cited first, 30 of 39)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://mlsanity.com/paper/1904.02701/) (2019)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)

## Built on by (most cited first, 28 of 28)

- [Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection](https://mlsanity.com/paper/2207.02541/) (2022)
- [Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection](https://mlsanity.com/paper/2209.01589/) (2022)
- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.04448/) (2022)
- [CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection](https://mlsanity.com/paper/2403.19278/) (2024)
- [Dynamic Curriculum Learning for Great Ape Detection in the Wild](https://mlsanity.com/paper/2205.00275/) (2022)
- [Mixed Pseudo Labels for Semi-Supervised Object Detection](https://mlsanity.com/paper/2312.07006/) (2023)
- [Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2401.05011/) (2024)
- [Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection](https://mlsanity.com/paper/2503.23220/) (2025)
- [Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty](https://mlsanity.com/paper/2212.02747/) (2022)
- [Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detection](https://mlsanity.com/paper/2306.02268/) (2023)
- [Semi-supervised Object Detection: A Survey on Recent Research and Progress](https://mlsanity.com/paper/2306.14106/) (2023)
- [Adaptive Self-Training for Object Detection](https://mlsanity.com/paper/2212.05911/) (2022)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Boosting Semi-Supervised 3D Object Detection with Semi-Sampling](https://mlsanity.com/paper/2211.07084/) (2022)
- [Pseudo-label Correction and Learning For Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.02998/) (2023)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [Semi-Supervised and Long-Tailed Object Detection with CascadeMatch](https://mlsanity.com/paper/2305.14813/) (2023)
- [LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection](https://mlsanity.com/paper/2509.16970/) (2025)
- [RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels](https://mlsanity.com/paper/2601.12715/) (2026)
- [Towards End-to-end Semi-supervised Learning for One-stage Object Detection](https://mlsanity.com/paper/2302.11299/) (2023)
- [Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection](https://mlsanity.com/paper/2303.11243/) (2023)
- [Training-based Model Refinement and Representation Disagreement for Semi-Supervised Object Detection](https://mlsanity.com/paper/2307.13755/) (2023)
- [Low-Confidence Samples Mining for Semi-supervised Object Detection](https://mlsanity.com/paper/2306.16201/) (2023)
- [Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Images](https://mlsanity.com/paper/2310.14718/) (2023)
- [Adversarial Attacked Teacher for Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2408.09431/) (2024)
- [Context Aware Grounded Teacher for Source Free Object Detection](https://mlsanity.com/paper/2504.15404/) (2025)
- [Aligned Consensus Teaching for Label-Efficient Oriented Object Detection in Weakly-Aligned Visible-Infrared Imagery](https://mlsanity.com/paper/2609.18124/) (2026)

## Abstract (arXiv)

This study delves into semi-supervised object detection (SSOD) to improve detector performance with additional unlabeled data. State-of-the-art SSOD performance has been achieved recently by self-training, in which training supervision consists of ground truths and pseudo-labels. In current studies, we observe that class imbalance in SSOD severely impedes the effectiveness of self-training. To address the class imbalance, we propose adaptive class-rebalancing self-training (ACRST) with a novel memory module called CropBank. ACRST adaptively rebalances the training data with foreground instances extracted from the CropBank, thereby alleviating the class imbalance. Owing to the high complexity of detection tasks, we observe that both self-training and data-rebalancing suffer from noisy pseudo-labels in SSOD. Therefore, we propose a novel two-stage filtering algorithm to generate accurate pseudo-labels. Our method achieves satisfactory improvements on MS-COCO and VOC benchmarks. When using only 1% labeled data in MS-COCO, our method achieves 17.02 mAP improvement over supervised baselines, and 5.32 mAP improvement compared with state-of-the-art methods.