# ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation

arXiv: https://arxiv.org/abs/2006.08658 · HTML: https://mlsanity.com/paper/2006.08658/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 27 of 27)

- [Learning to Track with Object Permanence](https://mlsanity.com/paper/2103.14258/) (2021)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2107.09600/) (2021)
- [Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation](https://mlsanity.com/paper/2101.07253/) (2021)
- [Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.06654/) (2022)
- [Geometric Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16694/) (2021)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2108.06962/) (2021)
- [Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation](https://mlsanity.com/paper/2106.15287/) (2021)
- [Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning](https://mlsanity.com/paper/2209.07774/) (2022)
- [Handling Out-of-Distribution Data: A Survey](https://mlsanity.com/paper/2507.21160/) (2025)
- [Continual Named Entity Recognition without Catastrophic Forgetting](https://mlsanity.com/paper/2310.14541/) (2023)
- [Approximately Bayes-Optimal Pseudo Label Selection](https://mlsanity.com/paper/2302.08883/) (2023)
- [Cross-Region Domain Adaptation for Class-level Alignment](https://mlsanity.com/paper/2109.06422/) (2021)
- [Self-Improving Semantic Perception for Indoor Localisation](https://mlsanity.com/paper/2105.01595/) (2021)
- [Uncertainty-Aware Semi-Supervised Few Shot Segmentation](https://mlsanity.com/paper/2110.08954/) (2021)
- [WDA-Net: Weakly-Supervised Domain Adaptive Segmentation of Electron Microscopy](https://mlsanity.com/paper/2210.13109/) (2022)
- [Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images](https://mlsanity.com/paper/2104.09699/) (2021)
- [Weakly-Supervised Cross-Domain Segmentation of Electron Microscopy with Sparse Point Annotation](https://mlsanity.com/paper/2404.00667/) (2024)
- [Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Tasks](https://mlsanity.com/paper/2407.01327/) (2024)
- [Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?](https://mlsanity.com/paper/2110.10369/) (2021)
- [Training Semantic Segmentation on Heterogeneous Datasets](https://mlsanity.com/paper/2301.07634/) (2023)
- [Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation](https://mlsanity.com/paper/2310.07149/) (2023)
- [Corporate Bankruptcy Prediction with Domain-Adapted BERT](https://mlsanity.com/paper/2312.03194/) (2023)
- [OurDB: Ouroboric Domain Bridging for Multi-Target Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2403.11582/) (2024)
- [Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier](https://mlsanity.com/paper/2606.16811/) (2026)

## Abstract (arXiv)

While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance. In addition, producing the extensive pixel-level annotations that the task requires comes at a great cost. Unsupervised domain adaptation (UDA) is one approach that tries to address these issues in order to make such systems more scalable. In particular, self-supervised learning (SSL) has recently become an effective strategy for UDA in semantic segmentation. At the core of such methods lies `pseudo-labeling', that is, the practice of assigning high-confident class predictions as pseudo-labels, subsequently used as true labels, for target data. To collect pseudo-labels, previous works often rely on the highest softmax score, which we here argue as an unfavorable confidence measurement. In this work, we propose Entropy-guided Self-supervised Learning (ESL), leveraging entropy as the confidence indicator for producing more accurate pseudo-labels. On different UDA benchmarks, ESL consistently outperforms strong SSL baselines and achieves state-of-the-art results.