首个同时优化四种数据增强自由度的可微方法，提升模型泛化能力。
FreeAugment: Data Augmentation Search Across All Degrees of Freedom
- 通过可微方法联合优化变换数量、类型、顺序和强度。
- 在多个图像基准上达到最优性能，超越现有方法。
- 适合需要高效自动增强的计算机视觉研究与应用。
数据增强已成为深度学习的重要组成部分，因其能提升神经网络的泛化能力。由于最有效的图像变换组合因任务和领域而异，自动化数据增强搜索旨在减轻手动寻找最优变换的繁重负担。然而，当前方法无法同时优化所有自由度：（1）应用变换的数量，（2）变换类型，（3）顺序，（4）强度。许多现有方法会重复选择相同变换，限制搜索仅两种变换，或以短视方式穷举或迭代搜索变换数量。我们的方法 FreeAugment 是首个使用全可微方法，同时实现对这四个自由度的全局优化。它高效学习变换数量及变换排列的概率分布，天然避免冗余重复并实现采样。实验表明，这种联合学习显著提升性能，在多种自然图像基准及其他领域均达到领先水平。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。