# Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning

arXiv: https://arxiv.org/abs/2303.01906 · HTML: https://mlsanity.com/paper/2303.01906/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 54 references that are in the map.
- First posted on arXiv 3 Mar 2023.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [ParseNet: Looking Wider to See Better](https://mlsanity.com/paper/1506.04579/) (2015)
- [Domain Generalization Using a Mixture of Multiple Latent Domains](https://mlsanity.com/paper/1911.07661/) (2019)
- [Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation](https://mlsanity.com/paper/2003.08040/) (2020)
- [Switchable Whitening for Deep Representation Learning](https://mlsanity.com/paper/1904.09739/) (2019)

## Built on by (most cited first, 11 of 11)

- [Frequency-aware Feature Fusion for Dense Image Prediction](https://mlsanity.com/paper/2408.12879/) (2024)
- [A Simple Recipe for Language-guided Domain Generalized Segmentation](https://mlsanity.com/paper/2311.17922/) (2023)
- [SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning](https://mlsanity.com/paper/2412.04077/) (2024)
- [Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning](https://mlsanity.com/paper/2403.06122/) (2024)
- [Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2412.12050/) (2024)
- [StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization](https://mlsanity.com/paper/2406.00275/) (2024)
- [LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives](https://mlsanity.com/paper/2503.18384/) (2025)
- [Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation](https://mlsanity.com/paper/2507.21367/) (2025)
- [Set Pivot Learning: Redefining Generalized Segmentation with Vision Foundation Models](https://mlsanity.com/paper/2508.01582/) (2025)
- [Domain Generalization for Semantic Segmentation: A Survey](https://mlsanity.com/paper/2510.03540/) (2025)
- [LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2608.08805/) (2026)

## Abstract (arXiv)

Deep networks trained on the source domain show degraded performance when tested on unseen target domain data. To enhance the model's generalization ability, most existing domain generalization methods learn domain invariant features by suppressing domain sensitive features. Different from them, we propose a Domain Projection and Contrastive Learning (DPCL) approach for generalized semantic segmentation, which includes two modules: Self-supervised Source Domain Projection (SSDP) and Multi-level Contrastive Learning (MLCL). SSDP aims to reduce domain gap by projecting data to the source domain, while MLCL is a learning scheme to learn discriminative and generalizable features on the projected data. During test time, we first project the target data by SSDP to mitigate domain shift, then generate the segmentation results by the learned segmentation network based on MLCL. At test time, we can update the projected data by minimizing our proposed pixel-to-pixel contrastive loss to obtain better results. Extensive experiments for semantic segmentation demonstrate the favorable generalization capability of our method on benchmark datasets.