GenLabel: Mixup Relabeling using Generative Models
read the original abstract
Mixup is a data augmentation method that generates new data points by mixing a pair of input data. While mixup generally improves the prediction performance, it sometimes degrades the performance. In this paper, we first identify the main causes of this phenomenon by theoretically and empirically analyzing the mixup algorithm. To resolve this, we propose GenLabel, a simple yet effective relabeling algorithm designed for mixup. In particular, GenLabel helps the mixup algorithm correctly label mixup samples by learning the class-conditional data distribution using generative models. Via extensive theoretical and empirical analysis, we show that mixup, when used together with GenLabel, can effectively resolve the aforementioned phenomenon, improving the generalization performance and the adversarial robustness.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Medical Model Synthesis Architectures: A Case Study
MedMSA framework retrieves knowledge via language models then builds formal probabilistic models to produce uncertainty-weighted differential diagnoses from symptoms.
-
Informational Frustration in Neural Manifolds: Shannon Bottlenecks and the Limits of Learnability
Introduces the Entropic Learnability Horizon and Shannon-Topological Bottleneck Theorem claiming that generalization fails via entropic phase transition to informational frustration when boundary complexity exceeds an...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.