Metasaug: Meta semantic augmentation for long-tailed visual recognition

S Li, K Gong, CH Liu, Y Wang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Real-world training data usually exhibits long-tailed distribution, where several majority
classes have a significantly larger number of samples than the remaining minority classes …
被引用次数：152 相关文章

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

S Li, K Gong, CH Liu, Y Wang, F Qiao… - 2021 IEEE/CVF …, 2021 - computer.org
Real-world training data usually exhibits long-tailed distribution, where several majority
classes have a significantly larger number of samples than the remaining minority classes …

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

S Li, K Gong, CH Liu, Y Wang, F Qiao… - arXiv preprint arXiv …, 2021 - arxiv.org
Real-world training data usually exhibits long-tailed distribution, where several majority
classes have a significantly larger number of samples than the remaining minority classes …

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

S Li, K Gong, CH Liu, Y Wang, F Qiao… - 2021 IEEE/CVF …, 2021 - ieeexplore.ieee.org
Real-world training data usually exhibits long-tailed distribution, where several majority
classes have a significantly larger number of samples than the remaining minority classes …
[PDF] researchgate.net

[PDF][PDF] MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

S Li, KGCH Liu, YWFQX Cheng - researchgate.net
Real-world training data usually exhibits long-tailed distribution, where several majority
classes have a significantly larger number of samples than the remaining minority classes …

MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

S Li, K Gong, CH Liu, Y Wang, F Qiao… - arXiv e …, 2021 - ui.adsabs.harvard.edu
Real-world training data usually exhibits long-tailed distribution, where several majority
classes have a significantly larger number of samples than the remaining minority classes …