# SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view images

arXiv: https://arxiv.org/abs/2509.02287 · HTML: https://mlsanity.com/paper/2509.02287/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments](https://mlsanity.com/paper/1811.10200/) (2018)
- [Unsupervised Domain Adaptation through Self-Supervision](https://mlsanity.com/paper/1909.11825/) (2019)
- [Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2204.02548/) (2022)
- [Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation](https://mlsanity.com/paper/2108.02376/) (2021)
- [Prompt-based Distribution Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2312.09553/) (2023)
- [Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization](https://mlsanity.com/paper/2108.08596/) (2021)
- [Feature Alignment and Restoration for Domain Generalization and Adaptation](https://mlsanity.com/paper/2006.12009/) (2020)
- [Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation](https://mlsanity.com/paper/2307.00371/) (2023)
- [Domain Generalization by Learning and Removing Domain-specific Features](https://mlsanity.com/paper/2212.07101/) (2022)
- [Domain Generalization through Meta-Learning: A Survey](https://mlsanity.com/paper/2404.02785/) (2024)
- [Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations](https://mlsanity.com/paper/2011.08502/) (2020)
- [Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2105.02001/) (2021)
- [Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning](https://mlsanity.com/paper/2403.06122/) (2024)
- [Augmentation-based Domain Generalization for Semantic Segmentation](https://mlsanity.com/paper/2304.12122/) (2023)
- [Domain Generalization with Small Data](https://mlsanity.com/paper/2402.06150/) (2024)
- [Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training](https://mlsanity.com/paper/2402.12187/) (2024)

## Abstract (arXiv)

Unstructured urban environments present unique challenges for scene understanding and generalization due to their complex and diverse layouts. We introduce SynthGenNet, a self-supervised student-teacher architecture designed to enable robust test-time domain generalization using synthetic multi-source imagery. Our contributions include the novel ClassMix++ algorithm, which blends labeled data from various synthetic sources while maintaining semantic integrity, enhancing model adaptability. We further employ Grounded Mask Consistency Loss (GMC), which leverages source ground truth to improve cross-domain prediction consistency and feature alignment. The Pseudo-Label Guided Contrastive Learning (PLGCL) mechanism is integrated into the student network to facilitate domain-invariant feature learning through iterative knowledge distillation from the teacher network. This self-supervised strategy improves prediction accuracy, addresses real-world variability, bridges the sim-to-real domain gap, and reliance on labeled target data, even in complex urban areas. Outcomes show our model outperforms the state-of-the-art (relying on single source) by achieving 50% Mean Intersection-Over-Union (mIoU) value on real-world datasets like Indian Driving Dataset (IDD).