论文标题
分布模型的荟萃分析
A Meta-Analysis of Distributionally-Robust Models
论文作者
论文摘要
在大规模数据集中训练的最先进的图像分类器（例如ImageNet）已被证明容易受到一系列故意和偶然分配变化的影响。另一方面，最近出现了一些具有良好分布（OOD）鲁棒性特性的分类器，在其目标任务上达到了高度准确性，同时保持其在挑战性基准方面的分配准确性。我们对广泛发布的模型进行了荟萃分析，其中大多数已在过去的十二个月中发表。通过这项荟萃分析，我们从经验上确定了所有表现最佳的OOD模型的四个主要共同点，所有这些模型都阐明了视力语言预训练的巨大希望。
State-of-the-art image classifiers trained on massive datasets (such as ImageNet) have been shown to be vulnerable to a range of both intentional and incidental distribution shifts. On the other hand, several recent classifiers with favorable out-of-distribution (OOD) robustness properties have emerged, achieving high accuracy on their target tasks while maintaining their in-distribution accuracy on challenging benchmarks. We present a meta-analysis on a wide range of publicly released models, most of which have been published over the last twelve months. Through this meta-analysis, we empirically identify four main commonalities for all the best-performing OOD-robust models, all of which illuminate the considerable promise of vision-language pre-training.
