arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.00136cs.LGcs.CV
收藏

IMB-NAS:不平衡数据集的神经架构搜索

IMB-NAS: Neural Architecture Search for Imbalanced Datasets

Georgia Institute of Technology(佐治亚理工学院)

Rahul Duggal, Shengyun Peng, Hao Zhou, Duen Horng Chau

摘要:

类不平衡是现实世界数据分布中普遍存在的现象。为了克服它对训练准确分类器的不利影响,现有的工作遵循三个主要方向:类重新平衡,信息传输和表示学习。在本文中,我们提出了一个新的补充方向,以提高长尾数据集的性能-通过神经架构搜索(NAS)优化骨干架构。我们发现,一个架构的准确性得到一个平衡的数据集并不表示良好的性能不平衡的。这就需要在长尾数据集上运行一个完整的NAS,因为长尾数据集可能会迅速变得计算密集。为了减轻这种计算负担,我们的目标是有效地适应NAS超级网络从一个平衡的源数据集到一个不平衡的目标。在几种自适应策略中,我们发现最有效的一种是重新训练线性分类头,重新加权损失,同时冻结在平衡源数据集上训练的骨干NAS超级网络。我们在多个数据集上进行了广泛的实验,并提供了具体的见解,以优化长尾数据集的架构。

英文摘要:

Class imbalance is a ubiquitous phenomenon occurring in real world data distributions. To overcome its detrimental effect on training accurate classifiers, existing work follows three major directions: class re-balancing, information transfer, and representation learning. In this paper, we propose a new and complementary direction for improving performance on long tailed datasets - optimizing the backbone architecture through neural architecture search (NAS). We find that an architecture's accuracy obtained on a balanced dataset is not indicative of good performance on imbalanced ones. This poses the need for a full NAS run on long tailed datasets which can quickly become prohibitively compute intensive. To alleviate this compute burden, we aim to efficiently adapt a NAS super-network from a balanced source dataset to an imbalanced target one. Among several adaptation strategies, we find that the most effective one is to retrain the linear classification head with reweighted loss, while freezing the backbone NAS super-network trained on a balanced source dataset. We perform extensive experiments on multiple datasets and provide concrete insights to optimize architectures for long tailed datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑