Gradient-based class weighting for unsupervised domain adaptation in dense prediction visual tasks
Open Access
- 17 April 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 166
Abstract
No abstract availableAll Related Versions
Funding Information
- Ministerio de Ciencia e Innovación (PID2021-125051OB-I00, TED2021-131643A-I00)
This publication has 39 references indexed in Scilit:
- A multi-grained unsupervised domain adaptation approach for semantic segmentationPattern Recognition, 2023
- Addressing the class-imbalance and class-overlap problems by a metaheuristic-based under-sampling approachPattern Recognition, 2023
- On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic dataMultimedia Tools and Applications, 2023
- MixGradient: A gradient-based re-weighting scheme with mixup for imbalanced data streamsNeural Networks, 2023
- HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation2022
- BP-triplet net for unsupervised domain adaptation: A Bayesian perspectivePattern Recognition, 2022
- A review of methods for imbalanced multi-label classificationPattern Recognition, 2021
- LOW: Training deep neural networks by learning optimal sample weightsPattern Recognition, 2021
- Playing for Data: Ground Truth from Computer Games2016
- Adapting Visual Category Models to New Domains2010