# Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes

arXiv: https://arxiv.org/abs/1707.09465 · HTML: https://mlsanity.com/paper/1707.09465/

## Key facts

- Cited by 105 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2017.

## Built on by (most cited first, 30 of 105)

- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation](https://mlsanity.com/paper/2104.10834/) (2021)
- [Semantic-Aware Domain Generalized Segmentation](https://mlsanity.com/paper/2204.00822/) (2022)
- [Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation](https://mlsanity.com/paper/2203.01452/) (2022)
- [Domain Adaptation for Time Series Forecasting via Attention Sharing](https://mlsanity.com/paper/2102.06828/) (2021)
- [Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2103.00236/) (2021)
- [Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation](https://mlsanity.com/paper/2108.02376/) (2021)
- [Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.09744/) (2022)
- [Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2303.14360/) (2023)
- [Style Normalization and Restitution for Domain Generalization and Adaptation](https://mlsanity.com/paper/2101.00588/) (2021)
- [Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2207.11860/) (2022)
- [Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2308.05493/) (2023)
- [Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.11062/) (2021)
- [Progressive Random Convolutions for Single Domain Generalization](https://mlsanity.com/paper/2304.00424/) (2023)
- [Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation](https://mlsanity.com/paper/2403.12505/) (2024)
- [Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.10856/) (2022)
- [Transformer-Based Source-Free Domain Adaptation](https://mlsanity.com/paper/2105.14138/) (2021)
- [GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation](https://mlsanity.com/paper/2403.16370/) (2024)
- [360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes](https://mlsanity.com/paper/2404.16501/) (2024)
- [WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation](https://mlsanity.com/paper/2109.14196/) (2021)
- [Generalized Domain Conditioned Adaptation Network](https://mlsanity.com/paper/2103.12339/) (2021)
- [Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning](https://mlsanity.com/paper/2210.09452/) (2022)
- [ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception](https://mlsanity.com/paper/2104.13395/) (2021)
- [AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection](https://mlsanity.com/paper/2106.05499/) (2021)
- [Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors](https://mlsanity.com/paper/2205.14467/) (2022)
- [Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagery](https://mlsanity.com/paper/2104.00564/) (2021)
- [Weakly supervised segmentation with cross-modality equivariant constraints](https://mlsanity.com/paper/2104.02488/) (2021)
- [Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters](https://mlsanity.com/paper/2207.01331/) (2022)
- [Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2308.11901/) (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. 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 cripples the models' performance. Hence, we propose a curriculum-style learning approach to minimize the domain gap in urban scenery 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.