mlsanityData to 7 Oct 2026

An Empirical Study on Multi-Domain Robust Semantic Segmentation

arXiv 2212.04221 ↗First posted 8 Dec 2022cs.CVcited by 2

Not on the map. Why?

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 37 of its 49 references that are in the map. First posted on arXiv 8 Dec 2022.

Builds on

37 of 49 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  8. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2019Invariant Risk Minimizationcited by 1,832
  11. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  12. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
25 more
  1. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  2. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  3. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  4. 2017Learning multiple visual domains with residual adapterscited by 553
  5. 2021Understanding Robustness of Transformers for Image Classificationcited by 250
  6. 2020Invariant Risk Minimization Gamescited by 188
  7. 2021Are Transformers More Robust Than CNNs?cited by 187
  8. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  9. 2017Playing for Benchmarkscited by 169
  10. 2018IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environmentscited by 163
  11. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  12. 2017Incremental Learning Through Deep Adaptationcited by 108
  13. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  14. 2018Visual Domain Adaptation with Manifold Embedded Distribution Alignmentcited by 91
  15. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  16. 2017Universal representations:The missing link between faces, text, planktons, and cat breedscited by 45
  17. 2019Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentationcited by 44
  18. 2019Transfer Learning with Dynamic Distribution Adaptationcited by 40
  19. 2021SimROD: A Simple Adaptation Method for Robust Object Detectioncited by 27
  20. 2019Budget-Aware Adapters for Multi-Domain Learningcited by 18
  21. 2019Efficient Multi-Domain Network Learning by Covariance Normalizationcited by 16
  22. 2021Multi-domain semantic segmentation with overlapping labelscited by 14
  23. 2016Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentationcited by 13
  24. 2020Multi-domain semantic segmentation with pyramidal fusioncited by 7
  25. 2022Automatic universal taxonomies for multi-domain semantic segmentationcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1.

2 papers.

  1. 2022Weakly supervised training of universal visual concepts for multi-domain semantic segmentationcited by 5
  2. 2024Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNscited by 2