# An Empirical Study on Multi-Domain Robust Semantic Segmentation

arXiv: https://arxiv.org/abs/2212.04221 · HTML: https://mlsanity.com/paper/2212.04221/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 49 references that are in the map.
- First posted on arXiv 8 Dec 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)
- [Invariant Risk Minimization Games](https://mlsanity.com/paper/2002.04692/) (2020)
- [Are Transformers More Robust Than CNNs?](https://mlsanity.com/paper/2111.05464/) (2021)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments](https://mlsanity.com/paper/1811.10200/) (2018)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [Incremental Learning Through Deep Adaptation](https://mlsanity.com/paper/1705.04228/) (2017)
- [Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning](https://mlsanity.com/paper/2110.05474/) (2021)
- [Visual Domain Adaptation with Manifold Embedded Distribution Alignment](https://mlsanity.com/paper/1807.07258/) (2018)
- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [Universal representations:The missing link between faces, text, planktons, and cat breeds](https://mlsanity.com/paper/1701.07275/) (2017)
- [Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation](https://mlsanity.com/paper/1902.07519/) (2019)
- [Transfer Learning with Dynamic Distribution Adaptation](https://mlsanity.com/paper/1909.08531/) (2019)

## Built on by (most cited first, 2 of 2)

- [Weakly supervised training of universal visual concepts for multi-domain semantic segmentation](https://mlsanity.com/paper/2212.10340/) (2022)
- [Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs](https://mlsanity.com/paper/2407.10534/) (2024)

## Abstract (arXiv)

How to effectively leverage the plentiful existing datasets to train a robust and high-performance model is of great significance for many practical applications. However, a model trained on a naive merge of different datasets tends to obtain poor performance due to annotation conflicts and domain divergence.In this paper, we attempt to train a unified model that is expected to perform well across domains on several popularity segmentation datasets.We conduct a detailed analysis of the impact on model generalization from three aspects of data augmentation, training strategies, and model capacity.Based on the analysis, we propose a robust solution that is able to improve model generalization across domains.Our solution ranks 2nd on RVC 2022 semantic segmentation task, with a dataset only 1/3 size of the 1st model used.