论文标题
混音：重新平衡混合
Remix: Rebalanced Mixup
论文作者
论文摘要
当训练数据严重失效时，深层图像分类器通常的性能往往很差。在这项工作中，我们提出了一种新的正则化技术混音，可放松混合的配方，并使特征和标签的混合因子被删除。具体而言，当混合两个样本（以与混合方式相同的方式）混合时，混音将标签分配给少数族裔类，通过为少数族裔提供不成比例的重量。通过这样做，分类器学会了将决策界限推向多数级别，并平衡多数族裔和少数族裔之间的概括错误。我们已经研究了在班级失情制度下的最先进的正规化技术，例如混合，歧管混合和cutmix，并表明，在Cifar-10，Cifar-10，Cifar-10和Cifar-100和acin-acin-acin-acin-acin-acin-acin ninicienciency-acin-acin-cifar-10上，在不平衡的数据集中，提出的混音显着超过了这些最先进和几种重新降低和重新采样技术。我们还评估了对现实世界中的大规模不平衡数据集的混音，《 inaturalist 2018》。实验结果证实，混音对先前方法提供了一致且显着的改进。
Deep image classifiers often perform poorly when training data are heavily class-imbalanced. In this work, we propose a new regularization technique, Remix, that relaxes Mixup's formulation and enables the mixing factors of features and labels to be disentangled. Specifically, when mixing two samples, while features are mixed in the same fashion as Mixup, Remix assigns the label in favor of the minority class by providing a disproportionately higher weight to the minority class. By doing so, the classifier learns to push the decision boundaries towards the majority classes and balance the generalization error between majority and minority classes. We have studied the state-of-the art regularization techniques such as Mixup, Manifold Mixup and CutMix under class-imbalanced regime, and shown that the proposed Remix significantly outperforms these state-of-the-arts and several re-weighting and re-sampling techniques, on the imbalanced datasets constructed by CIFAR-10, CIFAR-100, and CINIC-10. We have also evaluated Remix on a real-world large-scale imbalanced dataset, iNaturalist 2018. The experimental results confirmed that Remix provides consistent and significant improvements over the previous methods.
