# Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training

arXiv: https://arxiv.org/abs/1810.07911 · HTML: https://mlsanity.com/paper/1810.07911/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2018.

## Built on by (most cited first, 30 of 31)

- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [Bootstrapping Semantic Segmentation with Regional Contrast](https://mlsanity.com/paper/2104.04465/) (2021)
- [Semantic-Aware Domain Generalized Segmentation](https://mlsanity.com/paper/2204.00822/) (2022)
- [Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation](https://mlsanity.com/paper/2108.02376/) (2021)
- [Learning Cross-modal Contrastive Features for Video Domain Adaptation](https://mlsanity.com/paper/2108.11974/) (2021)
- [Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation](https://mlsanity.com/paper/2107.13780/) (2021)
- [LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.05570/) (2021)
- [Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning](https://mlsanity.com/paper/2104.11056/) (2021)
- [Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning](https://mlsanity.com/paper/2210.09452/) (2022)
- [Long-Tailed Anomaly Detection with Learnable Class Names](https://mlsanity.com/paper/2403.20236/) (2024)
- [Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation](https://mlsanity.com/paper/2405.15265/) (2024)
- [Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2102.13002/) (2021)
- [Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning](https://mlsanity.com/paper/2303.01906/) (2023)
- [Self-Supervised Learning of Domain Invariant Features for Depth Estimation](https://mlsanity.com/paper/2106.02594/) (2021)
- [Unsupervised Domain Adaptation for Video Semantic Segmentation](https://mlsanity.com/paper/2107.11052/) (2021)
- [Self-Improving Semantic Perception for Indoor Localisation](https://mlsanity.com/paper/2105.01595/) (2021)
- [Enhancing Counterfactual Classification via Self-Training](https://mlsanity.com/paper/2112.04461/) (2021)
- [SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets](https://mlsanity.com/paper/2308.11880/) (2023)
- [Weakly-Supervised Cross-Domain Segmentation of Electron Microscopy with Sparse Point Annotation](https://mlsanity.com/paper/2404.00667/) (2024)
- [Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression](https://mlsanity.com/paper/2401.13721/) (2024)
- [Probabilistic Domain Adaptation for Biomedical Image Segmentation](https://mlsanity.com/paper/2303.11790/) (2023)
- [Taking it further: leveraging pseudo labels for field delineation across label-scarce smallholder regions](https://mlsanity.com/paper/2312.08384/) (2023)
- [BIM Hyperreality: Data Synthesis Using BIM and Hyperrealistic Rendering for Deep Learning](https://mlsanity.com/paper/2105.04103/) (2021)
- [Dual-level Interaction for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2307.07972/) (2023)
- [ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA](https://mlsanity.com/paper/2211.08888/) (2022)
- [A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation](https://mlsanity.com/paper/2212.14154/) (2022)
- [Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis](https://mlsanity.com/paper/2312.02826/) (2023)
- [Test-Time Warmup for Multimodal Large Language Models](https://mlsanity.com/paper/2509.10641/) (2025)
- [Fairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification](https://mlsanity.com/paper/2510.10191/) (2025)
- [Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy](https://mlsanity.com/paper/2510.16450/) (2025)

## Abstract (arXiv)

Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world `wild tasks' where large difference between labeled training/source data and unseen test/target data exists. In particular, such difference is often referred to as `domain gap', and could cause significantly decreased performance which cannot be easily remedied by further increasing the representation power. Unsupervised domain adaptation (UDA) seeks to overcome such problem without target domain labels. In this paper, we propose a novel UDA framework based on an iterative self-training procedure, where the problem is formulated as latent variable loss minimization, and can be solved by alternatively generating pseudo labels on target data and re-training the model with these labels. On top of self-training, we also propose a novel class-balanced self-training framework to avoid the gradual dominance of large classes on pseudo-label generation, and introduce spatial priors to refine generated labels. Comprehensive experiments show that the proposed methods achieve state of the art semantic segmentation performance under multiple major UDA settings.