Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks. Over the years, the research community expands mix-up methods into two directions, with extensive efforts to improve saliency-guided procedures but minimal focus on the arbitrary path, leaving the randomization domain unexplored. In this paper, inspired by the superior qualities of each direction over one another, we introduce a novel method that lies at the junction of the two routes. By combining the best elements of randomness and saliency utilization, our method balances speed, simplicity, and accuracy. We name our method R-Mix following the concept of "Random Mix-up". We demonstrate its effectiveness in generalization, weakly supervised object localization, calibration, and robustness to adversarial attacks. Finally, in order to address the question of whether there exists a better decision protocol, we train a Reinforcement Learning agent that decides the mix-up policies based on the classifier's performance, reducing dependency on human-designed objectives and hyperparameter tuning. Extensive experiments further show that the agent is capable of performing at the cutting-edge level, laying the foundation for a fully automatic mix-up. Our code is released at [https://github.com/minhlong94/Random-Mixup].

翻译：混合增强训练方法已被证明能有效提升深度神经网络的泛化能力。多年来，研究界将混合方法扩展至两个方向：大量工作致力于改进显著性引导流程，但对随机路径的关注甚少，导致随机化领域尚待探索。受两类方法各自优势的启发，本文提出一种融合两条路径交界处的新方法。通过结合随机性与显著性利用的最佳元素，我们的方法在速度、简洁性和准确性之间实现了平衡。遵循"随机混合"的概念，我们将该方法命名为R-Mix。我们证明了其在泛化能力、弱监督目标定位、校准性以及对对抗攻击的鲁棒性方面的有效性。最后，为探究是否存在更优的决策协议，我们训练了一个基于分类器性能决策混合策略的强化学习智能体，减少了人工设计目标和超参数调优的依赖。大量实验进一步表明，该智能体能够达到前沿水平，为全自动混合方法奠定基础。我们的代码发布于[https://github.com/minhlong94/Random-Mixup]。