Multi-Sample $ζ$-mixup: Richer, More Realistic Synthetic Samples from a $p$-Series Interpolant
원문 초록
Modern deep learning training procedures rely on model regularization techniques such as data augmentation methods, which generate training samples that increase the diversity of data and richness of label information. A popular recent method, mixup, uses convex combinations of pairs of original samples to generate new samples. However, as we show in our experiments, mixup can produce undesirable synthetic samples, where the data is sampled off the manifold and can contain incorrect labels. We propose $\zeta$-mixup, a generalization of mixup with provably and demonstrably desirable properties that allows convex combinations of $N \geq 2$ samples, leading to more realistic and diverse outputs that incorporate information from $N$ original samples by using a $p$-series interpolant. We show that, compared to mixup, $\zeta$-mixup better preserves the intrinsic dimensionality of the original datasets, which is a desirable property for training generalizable models. Furthermore, we show that our implementation of $\zeta$-mixup is faster than mixup, and extensive evaluation on controlled synthetic and 24 real-world natural and medical image classification datasets shows that $\zeta$-mixup outperforms mixup and traditional data augmentation techniques.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Robust Training with Data Augmentation for Medical Imaging Classification
Adversarial attacks to image classification systems using evolutionary algorithms
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
Compositional Attribute Imbalance in Vision Datasets
Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach
토론
이 논문과 연결된 포럼 글이 아직 없습니다.