# A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/2012.00827 · HTML: https://mlsanity.com/paper/2012.00827/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

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

- [Semi-supervised Semantic Segmentation with Error Localization Network](https://mlsanity.com/paper/2204.02078/) (2022)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2306.04300/) (2023)
- [Diverse Cotraining Makes Strong Semi-Supervised Segmentor](https://mlsanity.com/paper/2308.09281/) (2023)
- [A Survey on Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2302.09899/) (2023)
- [Robust Mutual Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.00609/) (2021)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2111.10989/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross Teacher Training](https://mlsanity.com/paper/2209.01327/) (2022)
- [Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations](https://mlsanity.com/paper/2210.14670/) (2022)
- [Semi-supervised Semantic Segmentation for Remote Sensing Images via Multi-scale Uncertainty Consistency and Cross-Teacher-Student Attention](https://mlsanity.com/paper/2501.10736/) (2025)
- [Active Learning for Semantic Segmentation with Multi-class Label Query](https://mlsanity.com/paper/2309.09319/) (2023)
- [Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2307.09755/) (2023)
- [TrafficCAM: A Versatile Dataset for Traffic Flow Segmentation](https://mlsanity.com/paper/2211.09620/) (2022)
- [Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning](https://mlsanity.com/paper/2305.18158/) (2023)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2509.16704/) (2025)
- [Traffic Video Object Detection using Motion Prior](https://mlsanity.com/paper/2311.10092/) (2023)
- [PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2402.18117/) (2024)
- [DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation](https://mlsanity.com/paper/2507.10118/) (2025)
- [Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2408.02039/) (2024)
- [Multimodal Prototype Alignment for Semi-supervised Pathology Image Segmentation](https://mlsanity.com/paper/2508.19574/) (2025)
- [Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2309.12557/) (2023)
- [Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2404.02065/) (2024)
- [Bridging the Gaps: Utilizing Unlabeled Face Recognition Datasets to Boost Semi-Supervised Facial Expression Recognition](https://mlsanity.com/paper/2410.17622/) (2024)
- [MIPR:Automatic Annotation of Medical Images with Pixel Rearrangement](https://mlsanity.com/paper/2204.10513/) (2022)
- [A Robust Morphological Approach for Semantic Segmentation of Very High Resolution Images](https://mlsanity.com/paper/2208.01254/) (2022)
- [Calibrating Ensembles for Scalable Uncertainty Quantification in Deep Learning-based Medical Segmentation](https://mlsanity.com/paper/2209.09563/) (2022)
- [Harnessing Group-Oriented Consistency Constraints for Semi-Supervised Semantic Segmentation in CdZnTe Semiconductors](https://mlsanity.com/paper/2508.12766/) (2025)
- [FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation](https://mlsanity.com/paper/2510.02114/) (2025)

## Abstract (arXiv)

Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the cost of requiring a large set of high quality segmentation masks. To obtain such annotations is highly expensive and time consuming, in particular, in semantic segmentation where pixel-level annotations are required. In this work, we address this problem by proposing a holistic solution framed as a three-stage self-training framework for semi-supervised semantic segmentation. The key idea of our technique is the extraction of the pseudo-masks statistical information to decrease uncertainty in the predicted probability whilst enforcing segmentation consistency in a multi-task fashion. We achieve this through a three-stage solution. Firstly, we train a segmentation network to produce rough pseudo-masks which predicted probability is highly uncertain. Secondly, we then decrease the uncertainty of the pseudo-masks using a multi-task model that enforces consistency whilst exploiting the rich statistical information of the data. We compare our approach with existing methods for semi-supervised semantic segmentation and demonstrate its state-of-the-art performance with extensive experiments.