Mixup Without Hesitation

TL;DR

Mixup Without hesitation (mWh) is a new training algorithm that balances exploration and exploitation by gradually replacing mixup with basic augmentation, reducing training time and hyper-parameter tuning in image classification and other tasks.

Contribution

The paper introduces mWh, a simple and effective method that improves upon mixup by reducing training time and eliminating the need for hyper-parameter tuning.

Findings

mWh achieves comparable or better accuracy than mixup with less training time.

mWh transfers well to CutMix and other vision tasks, improving performance.

It acts as a hyper-parameter-free alternative to mixup, simplifying training.

Abstract

Mixup linearly interpolates pairs of examples to form new samples, which is easy to implement and has been shown to be effective in image classification tasks. However, there are two drawbacks in mixup: one is that more training epochs are needed to obtain a well-trained model; the other is that mixup requires tuning a hyper-parameter to gain appropriate capacity but that is a difficult task. In this paper, we find that mixup constantly explores the representation space, and inspired by the exploration-exploitation dilemma in reinforcement learning, we propose mixup Without hesitation (mWh), a concise, effective, and easy-to-use training algorithm. We show that mWh strikes a good balance between exploration and exploitation by gradually replacing mixup with basic data augmentation. It can achieve a strong baseline with less training time than original mixup and without searching for optimal hyper-parameter, i.e., mWh acts as mixup without hesitation. mWh can also transfer to CutMix, and gain consistent improvement on other machine learning and computer vision tasks such as object detection. Our code is open-source and available at https://github.com/yuhao318/mwh