# Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes

arXiv: https://arxiv.org/abs/1904.09092 · HTML: https://mlsanity.com/paper/1904.09092/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2019.

## Built on by (most cited first, 23 of 23)

- [Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation](https://mlsanity.com/paper/2312.03502/) (2023)
- [DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing](https://mlsanity.com/paper/2201.01047/) (2022)
- [Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters](https://mlsanity.com/paper/2207.01331/) (2022)
- [Gaussian Dynamic Convolution for Efficient Single-Image Segmentation](https://mlsanity.com/paper/2104.08783/) (2021)
- [Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation](https://mlsanity.com/paper/2103.15685/) (2021)
- [ASK: Adaptively Selecting Key Local Features for RGB-D Scene Recognition](https://mlsanity.com/paper/2110.07703/) (2021)
- [Curriculum-style Local-to-global Adaptation for Cross-domain Remote Sensing Image Segmentation](https://mlsanity.com/paper/2203.01539/) (2022)
- [Deep Transfer Learning for Intelligent Vehicle Perception: a Survey](https://mlsanity.com/paper/2306.15110/) (2023)
- [WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection](https://mlsanity.com/paper/2407.20818/) (2024)
- [PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies](https://mlsanity.com/paper/2506.09237/) (2025)
- [Self-Ensembling GAN for Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2112.07999/) (2021)
- [BiP-Net: Bidirectional Perspective Strategy based Arbitrary-Shaped Text Detection Network](https://mlsanity.com/paper/2104.04903/) (2021)
- [Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic](https://mlsanity.com/paper/2310.04416/) (2023)
- [SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World Model](https://mlsanity.com/paper/2503.13952/) (2025)
- [A Novel Incremental Learning Driven Instance Segmentation Framework to Recognize Highly Cluttered Instances of the Contraband Items](https://mlsanity.com/paper/2201.02560/) (2022)
- [Weakly-supervised continual learning for class-incremental segmentation](https://mlsanity.com/paper/2201.01029/) (2022)
- [Labeling Where Adapting Fails: Cross-Domain Semantic Segmentation with Point Supervision via Active Selection](https://mlsanity.com/paper/2206.00181/) (2022)
- [MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2309.11711/) (2023)
- [Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2408.02039/) (2024)
- [Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.04523/) (2021)
- [Deep Image Semantic Communication Model for Artificial Intelligent Internet of Things](https://mlsanity.com/paper/2311.02926/) (2023)
- [Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning](https://mlsanity.com/paper/2302.08710/) (2023)
- [Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations](https://mlsanity.com/paper/2401.01035/) (2024)

## Abstract (arXiv)

Semantic segmentation, a pixel-level vision task, is developed rapidly by using convolutional neural networks (CNNs). Training CNNs requires a large amount of labeled data, but manually annotating data is difficult. For emancipating manpower, in recent years, some synthetic datasets are released. However, they are still different from real scenes, which causes that training a model on the synthetic data (source domain) cannot achieve a good performance on real urban scenes (target domain). In this paper, we propose a weakly supervised adversarial domain adaptation to improve the segmentation performance from synthetic data to real scenes, which consists of three deep neural networks. To be specific, a detection and segmentation ("DS" for short) model focuses on detecting objects and predicting segmentation map; a pixel-level domain classifier ("PDC" for short) tries to distinguish the image features from which domains; an object-level domain classifier ("ODC" for short) discriminates the objects from which domains and predicts the objects classes. PDC and ODC are treated as the discriminators, and DS is considered as the generator. By adversarial learning, DS is supposed to learn domain-invariant features. In experiments, our proposed method yields the new record of mIoU metric in the same problem.