# CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation

arXiv: https://arxiv.org/abs/2208.14227 · HTML: https://mlsanity.com/paper/2208.14227/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 60 references that are in the map.
- First posted on arXiv 27 Aug 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2011.10043/) (2020)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data](https://mlsanity.com/paper/1904.00592/) (2019)
- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)

## Built on by (most cited first, 13 of 13)

- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Vision transformers in domain adaptation and domain generalization: a study of robustness](https://mlsanity.com/paper/2404.04452/) (2024)
- [Exploring the Benefits of Vision Foundation Models for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2406.09896/) (2024)
- [ProtoGMM: Multi-prototype Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation](https://mlsanity.com/paper/2406.19225/) (2024)
- [We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline](https://mlsanity.com/paper/2402.00868/) (2024)
- [Dual-level Interaction for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2307.07972/) (2023)
- [SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation](https://mlsanity.com/paper/2311.10806/) (2023)
- [Unsupervised Domain Adaptive Lane Detection via Contextual Contrast and Aggregation](https://mlsanity.com/paper/2407.13328/) (2024)
- [GenGMM: Generalized Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation](https://mlsanity.com/paper/2410.16485/) (2024)
- [Adversarially Domain-adaptive Latent Diffusion for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2412.16859/) (2024)
- [VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2503.10685/) (2025)
- [What is the Added Value of UDA in the VFM Era?](https://mlsanity.com/paper/2504.18190/) (2025)
- [Target-specific Adaptation and Consistent Degradation Alignment for Cross-Domain Remaining Useful Life Prediction](https://mlsanity.com/paper/2512.02610/) (2025)

## Abstract (arXiv)

In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of pseudo-labels generated from the target domain by the teacher network. More specifically, we extract a multi-level fused-feature map from the encoder, and apply contrastive loss across different classes and different domains, via source-target mixing of images. We consistently improve performance on various feature encoder architectures and for different domain adaptation datasets in semantic segmentation. Furthermore, we introduce a learned-weighted contrastive loss to improve upon on a state-of-the-art multi-resolution training approach in UDA. We produce state-of-the-art results on GTA rightarrow Cityscapes (74.4 mIOU, +0.6) and Synthia rightarrow Cityscapes (67.2 mIOU, +1.4) datasets. CLUDA effectively demonstrates contrastive learning in UDA as a generic method, which can be easily integrated into any existing UDA for semantic segmentation tasks. Please refer to the supplementary material for the details on implementation.