# Improving Semantic Segmentation via Self-Training

arXiv: https://arxiv.org/abs/2004.14960 · HTML: https://mlsanity.com/paper/2004.14960/

## Key facts

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

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

- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.09025/) (2021)
- [Bootstrapping Semantic Segmentation with Regional Contrast](https://mlsanity.com/paper/2104.04465/) (2021)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations](https://mlsanity.com/paper/2207.05027/) (2022)
- [Progressive Coordinate Transforms for Monocular 3D Object Detection](https://mlsanity.com/paper/2108.05793/) (2021)
- [MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2103.05254/) (2021)
- [Video Mask Transfiner for High-Quality Video Instance Segmentation](https://mlsanity.com/paper/2207.14012/) (2022)
- [COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical Image Segmentation based on Target-aware Domain Translation and Iterative Self-Training](https://mlsanity.com/paper/2203.16557/) (2022)
- [Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking](https://mlsanity.com/paper/2204.07049/) (2022)
- [Decoder Denoising Pretraining for Semantic Segmentation](https://mlsanity.com/paper/2205.11423/) (2022)
- [A Unified Efficient Pyramid Transformer for Semantic Segmentation](https://mlsanity.com/paper/2107.14209/) (2021)
- [CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2208.14227/) (2022)
- [Semi-Supervised Semantic Segmentation with Cross Teacher Training](https://mlsanity.com/paper/2209.01327/) (2022)
- [SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation](https://mlsanity.com/paper/2305.11012/) (2023)
- [Multi-Object Tracking with Hallucinated and Unlabeled Videos](https://mlsanity.com/paper/2108.08836/) (2021)
- [Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.11145/) (2023)
- [Revisiting consistency for semi-supervised semantic segmentation](https://mlsanity.com/paper/2106.07075/) (2021)
- [Semi-supervised Learning using Robust Loss](https://mlsanity.com/paper/2203.01524/) (2022)
- [Open Vocabulary Semantic Scene Sketch Understanding](https://mlsanity.com/paper/2312.12463/) (2023)
- [Semantic Segmentation with Active Semi-Supervised Representation Learning](https://mlsanity.com/paper/2210.08403/) (2022)
- [STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization](https://mlsanity.com/paper/2201.05121/) (2022)
- [Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation](https://mlsanity.com/paper/2407.12630/) (2024)
- [AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.13227/) (2021)
- [Multi-Class 3D Object Detection with Single-Class Supervision](https://mlsanity.com/paper/2205.05703/) (2022)
- [Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2404.02065/) (2024)
- [MIPR:Automatic Annotation of Medical Images with Pixel Rearrangement](https://mlsanity.com/paper/2204.10513/) (2022)
- [Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images](https://mlsanity.com/paper/2211.07491/) (2022)
- [Mind the Context: Attention-Guided Weak-to-Strong Consistency for Enhanced Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2410.12419/) (2024)
- [Can Unsupervised Segmentation Reduce Annotation Costs for Video Semantic Segmentation?](https://mlsanity.com/paper/2603.27697/) (2026)

## Abstract (arXiv)

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets while requiring significantly less supervision. We also demonstrate the effectiveness of self-training on a challenging cross-domain generalization task, outperforming conventional finetuning method by a large margin. Lastly, to alleviate the computational burden caused by the large amount of pseudo labels, we propose a fast training schedule to accelerate the training of segmentation models by up to 2x without performance degradation.