GenLabel: Mixup Relabeling using Generative Models

2022-01-07 · Jy-yong Sohn, Liang Shang, Hongxu Chen, Jaekyun Moon, Dimitris Papailiopoulos, Kangwook Lee

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.

📄 PDF Abstract BibTeX arXiv:2201.02354

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness Data Augmentation

Methods 이 논문이 사용한 방법론

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…

Global Mixup: Eliminating Ambiguity with Clustering

2022-06-06 · Xiangjin Xie, Yangning Li, Wang Chen, Kai Ouyang 외

Data augmentation with \textbf{Mixup} has been proven an effective method to regularize the current deep neural networks. Mixup generates virtual samples and corresponding labels at once through linear interpolation. How…

Clustering Data Augmentation

mixup: Beyond Empirical Risk Minimization

2017-10-25 · ICLR 2018 1 · Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issu…

Domain Generalization Image Classification Memorization Out-of-Distribution Generalization+1

SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling

2024-10-16 · Loris Gaven, Clement Romac, Thomas Carta, Sylvain Lamprier 외

The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex environments where their zero-shot abili…

Decision Making Reinforcement Learning (RL)Sequential Decision Making

On the benefits of defining vicinal distributions in latent space

2020-03-14 · Puneet Mangla, Vedant Singh, Shreyas Jayant Havaldar, Vineeth N. Balasubramanian

The vicinal risk minimization (VRM) principle is an empirical risk minimization (ERM) variant that replaces Dirac masses with vicinal functions. There is strong numerical and theoretical evidence showing that VRM outperf…

Hindsight Foresight Relabeling for Meta-Reinforcement Learning

2021-09-18 · ICLR 2022 4 · Michael Wan, Jian Peng, Tanmay Gangwani

Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL. However, while meta-RL agents can adapt quickly…

Meta Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)