Label Calibration for Semantic Segmentation Under Domain Shift
Not on the map. Why?
Abstract (arXiv)
Performance of a pre-trained semantic segmentation model is likely to substantially decrease on data from a new domain. We show a pre-trained model can be adapted to unlabelled target domain data by calculating soft-label prototypes under the domain shift and making predictions according to the prototype closest to the vector with predicted class probabilities. The proposed adaptation procedure is fast, comes almost for free in terms of computational resources and leads to considerable performance improvements. We demonstrate the benefits of such label calibration on the highly-practical synthetic-to-real semantic segmentation problem.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 19 of its 23 references that are in the map. First posted on arXiv 20 Jul 2023.
Builds on
19 of 23 references.
References · 19
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
- 2015Domain-Adversarial Training of Neural Networkscited by 3,044
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
- 2020In Search of Lost Domain Generalizationcited by 1,054
- 2016End to End Learning for Self-Driving Carscited by 1,009
- 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
- 2016Playing for Data: Ground Truth from Computer Gamescited by 818
- 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
- 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
- 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 336
7 more
- 2020Universal Source-Free Domain Adaptationcited by 220
- 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
- 2019A review of domain adaptation without target labelscited by 156
- 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
- 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
- 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
- 2018Style Augmentation: Data Augmentation via Style Randomizationcited by 79
Built on by
Citing papers per year: 2024: 2.
2 papers.