Few-shot learning with noisy labels

KJ Liang, SB Rangrej, V Petrovic… - Proceedings of the …, 2022 - openaccess.thecvf.com
Few-shot learning (FSL) methods typically assume clean support sets with accurately
labeled samples when training on novel classes. This assumption can often be unrealistic …
被引用次数：52 相关文章

Few-shot Learning with Noisy Labels

KJ Liang, SB Rangrej, V Petrovic… - 2022 IEEE/CVF …, 2022 - ieeexplore.ieee.org
Few-shot learning (FSL) methods typically assume clean support sets with accurately
labeled samples when training on novel classes. This assumption can often be unrealistic …

Few-shot Learning with Noisy Labels

KJ Liang, SB Rangrej, V Petrovic, T Hassner - arXiv preprint arXiv …, 2022 - arxiv.org
Few-shot learning (FSL) methods typically assume clean support sets with accurately
labeled samples when training on novel classes. This assumption can often be unrealistic …

Few-shot Learning with Noisy Labels

KJ Liang, SB Rangrej, V Petrovic… - 2022 IEEE/CVF …, 2022 - computer.org
Few-shot learning (FSL) methods typically assume clean support sets with accurately
labeled samples when training on novel classes. This assumption can often be unrealistic …
[PDF] github.io

[PDF][PDF] Few-shot Learning with Noisy Labels

KJ Liang, SB Rangrej, V Petrovic, T Hassner - kevinjliang.github.io
Few-shot learning (FSL) methods typically assume clean support sets with accurately
labeled samples when training on novel classes. This assumption can often be unrealistic …

Few-shot Learning with Noisy Labels

KJ Liang, SB Rangrej, V Petrovic, T Hassner - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Few-shot learning (FSL) methods typically assume clean support sets with accurately
labeled samples when training on novel classes. This assumption can often be unrealistic …