# Debiased Self-Training for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/2202.07136 · HTML: https://mlsanity.com/paper/2202.07136/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 80 references that are in the map.
- First posted on arXiv 15 Feb 2022.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [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)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Adversarially Learned Inference](https://mlsanity.com/paper/1606.00704/) (2016)

## Built on by (most cited first, 30 of 62)

- [Self-Training: A Survey](https://mlsanity.com/paper/2202.12040/) (2022)
- [Test-Time Adaptation via Self-Training with Nearest Neighbor Information](https://mlsanity.com/paper/2207.10792/) (2022)
- [ProMix: Combating Label Noise via Maximizing Clean Sample Utility](https://mlsanity.com/paper/2207.10276/) (2022)
- [Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels](https://mlsanity.com/paper/2302.10586/) (2023)
- [Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2310.11320/) (2023)
- [Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning](https://mlsanity.com/paper/2306.01669/) (2023)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2307.11960/) (2023)
- [Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner](https://mlsanity.com/paper/2305.01711/) (2023)
- [FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning](https://mlsanity.com/paper/2310.16412/) (2023)
- [Rethinking Semi-supervised Learning with Language Models](https://mlsanity.com/paper/2305.13002/) (2023)
- [Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics](https://mlsanity.com/paper/2505.12709/) (2025)
- [SemiReward: A General Reward Model for Semi-supervised Learning](https://mlsanity.com/paper/2310.03013/) (2023)
- [An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2211.11086/) (2022)
- [360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentation](https://mlsanity.com/paper/2309.06197/) (2023)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [Boosting Cross-Domain Speech Recognition with Self-Supervision](https://mlsanity.com/paper/2206.09783/) (2022)
- [Rethinking Chain-of-Thought from the Perspective of Self-Training](https://mlsanity.com/paper/2412.10827/) (2024)
- [Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators](https://mlsanity.com/paper/2307.05358/) (2023)
- [Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation](https://mlsanity.com/paper/2406.06813/) (2024)
- [Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias](https://mlsanity.com/paper/2310.14814/) (2023)
- [Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction:A Multi-Dataset Study](https://mlsanity.com/paper/2306.10494/) (2023)
- [PrevMatch: Revisiting and Maximizing Temporal Knowledge in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2405.20610/) (2024)
- [S4DL: Shift-sensitive Spatial-Spectral Disentangling Learning for Hyperspectral Image Unsupervised Domain Adaptation](https://mlsanity.com/paper/2408.15263/) (2024)
- [Dual Classification Head Self-training Network for Cross-scene Hyperspectral Image Classification](https://mlsanity.com/paper/2502.17879/) (2025)
- [Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization](https://mlsanity.com/paper/2506.02334/) (2025)
- [When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2509.16704/) (2025)
- [Addressing Distribution Shift at Test Time in Pre-trained Language Models](https://mlsanity.com/paper/2212.02384/) (2022)
- [Language Semantic Graph Guided Data-Efficient Learning](https://mlsanity.com/paper/2311.08782/) (2023)
- [DTBS: Dual-Teacher Bi-directional Self-training for Domain Adaptation in Nighttime Semantic Segmentation](https://mlsanity.com/paper/2401.01066/) (2024)

## Abstract (arXiv)

Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement for labeled data, self-training is widely used in semi-supervised learning by iteratively assigning pseudo labels to unlabeled samples. Despite its popularity, self-training is well-believed to be unreliable and often leads to training instability. Our experimental studies further reveal that the bias in semi-supervised learning arises from both the problem itself and the inappropriate training with potentially incorrect pseudo labels, which accumulates the error in the iterative self-training process. To reduce the above bias, we propose Debiased Self-Training (DST). First, the generation and utilization of pseudo labels are decoupled by two parameter-independent classifier heads to avoid direct error accumulation. Second, we estimate the worst case of self-training bias, where the pseudo labeling function is accurate on labeled samples, yet makes as many mistakes as possible on unlabeled samples. We then adversarially optimize the representations to improve the quality of pseudo labels by avoiding the worst case. Extensive experiments justify that DST achieves an average improvement of 6.3% against state-of-the-art methods on standard semi-supervised learning benchmark datasets and 18.9% against FixMatch on 13 diverse tasks. Furthermore, DST can be seamlessly adapted to other self-training methods and help stabilize their training and balance performance across classes in both cases of training from scratch and finetuning from pre-trained models.