FreeAugment：跨所有自由度的数据增强搜索
FreeAugment: Data Augmentation Search Across All Degrees of Freedom
AI总结：
本文提出 FreeAugment，一种完全可微的自动数据增强搜索方法，首次同时全局优化变换数量、类型、顺序和幅度，并在多领域基准上达到最先进性能。
摘要：
数据增强已成为深度学习不可或缺的一部分，因为众所周知它能够提升神经网络的泛化能力。由于最有效的图像变换集合在不同任务和领域之间存在差异，自动化数据增强搜索旨在减轻人工寻找最优图像变换的极端负担。然而，当前方法无法联合优化所有自由度：（1）要应用的变换数量、其（2）类型、（3）顺序以及（4）幅度。许多现有方法存在多次选择同一变换的风险，将搜索限制为仅两个变换，或者以短视方式穷举或迭代地搜索变换数量。我们的方法 FreeAugment 是首个使用完全可微方法同时实现全部四个自由度全局优化的方法。它高效地学习变换数量及其排列上的概率分布，在采样时从根本上避免冗余重复。我们的实验表明，这种对所有自由度的联合学习显著提升了性能，在各种自然图像基准以及其他领域的基准上取得了最先进结果。项目页面位于 https://tombekor.github.io/FreeAugment-web。
英文摘要：
Data augmentation has become an integral part of deep learning, as it is known to improve the generalization capabilities of neural networks. Since the most effective set of image transformations differs between tasks and domains, automatic data augmentation search aims to alleviate the extreme burden of manually finding the optimal image transformations. However, current methods are not able to jointly optimize all degrees of freedom: (1) the number of transformations to be applied, their (2) types, (3) order, and (4) magnitudes. Many existing methods risk picking the same transformation more than once, limit the search to two transformations only, or search for the number of transformations exhaustively or iteratively in a myopic manner. Our approach, FreeAugment, is the first to achieve global optimization of all four degrees of freedom simultaneously, using a fully differentiable method. It efficiently learns the number of transformations and a probability distribution over their permutations, inherently refraining from redundant repetition while sampling. Our experiments demonstrate that this joint learning of all degrees of freedom significantly improves performance, achieving state-of-the-art results on various natural image benchmarks and beyond across other domains. Project page at https://tombekor.github.io/FreeAugment-web
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。
