解决随机增强的特征遗忘问题，提升其泛化能力
Dealing with the Evil Twins: Improving Random Augmentation by Addressing Catastrophic Forgetting of Diverse Augmentations
- 发现随机增强因冲突扰动导致特征扭曲，类似灾难性遗忘
- 通过缓解遗忘机制，显著提升随机增强在sDG任务上的表现
- 适合追求高效、低成本增强策略的研究者和工程应用
数据增强是提升分布外泛化能力的有效手段，关键在于通过高成本的定向增强生成多样且具挑战性的源域变体以最大化泛化效果。相反，随机增强虽成本低但被认为效果有限。本文重新审视随机增强，揭示其随机性可能导致一组相互冲突的增强操作，扭曲模型学习到的特征，类似于灾难性遗忘。为此，我们提出一种简单有效的解决方案，通过缓解遗忘现象来提升随机增强的泛化性能，在多个单源域泛化（sDG）基准上均表现出色。
原文摘要 · Abstract (English)
Data augmentation is a promising tool for enhancing out-of-distribution generalization, where the key is to produce diverse, challenging variations of the source domain via costly targeted augmentations that maximize its generalization effect. Conversely, random augmentation is inexpensive but is deemed suboptimal due to its limited effect. In this paper, we revisit random augmentation and explore methods to address its shortcomings. We show that the stochastic nature of random augmentation can produce a set of colliding augmentations that distorts the learned features, similar to catastrophic forgetting. We propose a simple solution that improves the generalization effect of random augmentation by addressing forgetting, which displays strong generalization performance across various single source domain generalization (sDG) benchmarks.
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。