# A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes

arXiv: https://arxiv.org/abs/1812.09953 · HTML: https://mlsanity.com/paper/1812.09953/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2018.

## Built on by (most cited first, 30 of 43)

- [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)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [Multi-Target Domain Adaptation with Collaborative Consistency Learning](https://mlsanity.com/paper/2106.03418/) (2021)
- [Self-Adversarial Disentangling for Specific Domain Adaptation](https://mlsanity.com/paper/2108.03553/) (2021)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data](https://mlsanity.com/paper/2112.00054/) (2021)
- [Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2108.12545/) (2021)
- [Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection](https://mlsanity.com/paper/2103.14198/) (2021)
- [Hidden Backdoor Attack against Semantic Segmentation Models](https://mlsanity.com/paper/2103.04038/) (2021)
- [Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation](https://mlsanity.com/paper/2308.14619/) (2023)
- [Domain Generalization via Balancing Training Difficulty and Model Capability](https://mlsanity.com/paper/2309.00844/) (2023)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Test-Time Adaptation with Shape Moments for Image Segmentation](https://mlsanity.com/paper/2205.07983/) (2022)
- [Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinement](https://mlsanity.com/paper/2310.16979/) (2023)
- [Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2105.05013/) (2021)
- [AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2107.10140/) (2021)
- [Inter-Domain Mixup for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2401.11453/) (2024)
- [Simulation-to-Real domain adaptation with teacher-student learning for endoscopic instrument segmentation](https://mlsanity.com/paper/2103.01593/) (2021)
- [Personalized Image Semantic Segmentation](https://mlsanity.com/paper/2107.13978/) (2021)
- [Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning](https://mlsanity.com/paper/2306.01598/) (2023)
- [Long-tailed Distribution Adaptation](https://mlsanity.com/paper/2110.02686/) (2021)
- [Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion](https://mlsanity.com/paper/2206.04879/) (2022)
- [Self-Ensembling GAN for Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2112.07999/) (2021)
- [FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images](https://mlsanity.com/paper/2201.02588/) (2022)
- [Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2201.06974/) (2022)
- [Multi-level Domain Adaptation for Lane Detection](https://mlsanity.com/paper/2206.10692/) (2022)
- [Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations](https://mlsanity.com/paper/2108.03021/) (2021)
- [Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration](https://mlsanity.com/paper/2406.01601/) (2024)
- [Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2308.15353/) (2023)

## Abstract (arXiv)

During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving and augmented reality. However, to train CNNs requires a considerable amount of data, which is difficult to collect and laborious to annotate. Recent advances in computer graphics make it possible to train CNNs on photo-realistic synthetic imagery with computer-generated annotations. Despite this, the domain mismatch between the real images and the synthetic data hinders the models' performance. Hence, we propose a curriculum-style learning approach to minimizing the domain gap in urban scene semantic segmentation. The curriculum domain adaptation solves easy tasks first to infer necessary properties about the target domain; in particular, the first task is to learn global label distributions over images and local distributions over landmark superpixels. These are easy to estimate because images of urban scenes have strong idiosyncrasies (e.g., the size and spatial relations of buildings, streets, cars, etc.). We then train a segmentation network, while regularizing its predictions in the target domain to follow those inferred properties. In experiments, our method outperforms the baselines on two datasets and two backbone networks. We also report extensive ablation studies about our approach.