CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
Sangdoo Yun1 Dongyoon Han1 Seong Joon Oh2 Sanghyuk Chun1 Junsuk Choe1,3 Youngjoon Yoo1 1Clova AI Research, NAVER Corp. 2Clova AI Research, LINE Plus Corp. 3Yonsei University
Abstract
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to attend on less discriminative parts of objects (e.g. leg as opposed to head of a person), thereby letting the network generalize better and have better object localization capabilities. On the other hand, current methods for regional dropout remove informative pixels on training images by overlaying a patch of either black pixels or random noise. Such removal is not desirable because it leads to information loss and inefficiency during training. We therefore propose the CutMix augmentation strategy: patches are cut and pasted among training images where the ground truth labels are also mixed proportionally to the area of the patches. By making efficient use of training pixels and retaining the regularization effect of regional dropout, CutMix consistently outperforms the state-of-the-art augmentation strategies on CIFAR and ImageNet classification tasks, as well as on the ImageNet weakly-supervised localization task. Moreover, unlike previous augmentation methods, our CutMix-trained ImageNet classifier, when
中文速览
训练图像分类神经网络时，现有的"区域遮挡"正则化方法（如Cutout）会把图片的某块区域直接涂黑或填随机噪声，白白浪费了大量像素信息。CutMix提出了一个更聪明的做法：把一张图片裁下的矩形块粘贴到另一张图片对应位置，同时按两张图各自占用的像素比例混合标签，让每一个训练像素都得到充分利用。实验结果显示，CutMix在CIFAR-100、ImageNet分类、弱监督目标定位等多项任务上均超越了Mixup、Cutout等主流数据增强方法，以ImageNet上的ResNet-50为例，top-1准确率提升了2.28%，迁移到Pascal VOC目标检测和MS-COCO图像描述任务后也带来了稳定增益。这一方法之所以重要，在于它用极低的额外计算开销同时兼顾了数据利用效率、模型泛化能力和定位能力，是一种可以即插即用的通用训练技巧。
原文 arXiv:1905.04899;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1905.04899v2