MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition

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. This imbalance degrades the performance of typical supervised learning algorithms designed for balanced training sets....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 5208 - 5217
Hlavní autoři: Li, Shuang, Gong, Kaixiong, Liu, Chi Harold, Wang, Yulin, Qiao, Feng, Cheng, Xinjing
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2021
Témata:
Benchmark testing
Computer vision
Semantics
Supervised learning
Training
Training data
Visualization
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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. This imbalance degrades the performance of typical supervised learning algorithms designed for balanced training sets. In this paper, we address this issue by augmenting minority classes with a recently proposed implicit semantic data augmentation (ISDA) algorithm [37], which produces diversified augmented samples by translating deep features along many semantically meaningful directions. Importantly, given that ISDA estimates the class-conditional statistics to obtain semantic directions, we find it ineffective to do this on minority classes due to the insufficient training data. To this end, we propose a novel approach to learn transformed semantic directions with meta-learning automatically. In specific, the augmentation strategy during training is dynamically optimized, aiming to minimize the loss on a small balanced validation set, which is approximated via a meta update step. Extensive empirical results on CIFAR-LT-10/100, ImageNet-LT, and iNaturalist 2017/2018 validate the effectiveness of our method.
ISSN:1063-6919
DOI:10.1109/CVPR46437.2021.00517