PLACE dropout：一种用于领域泛化的渐进式逐层逐通道 Dropout
PLACE dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization
AI总结：
本文提出 PLACE dropout，通过随机选择层和通道进行 dropout 并结合渐进式比率提升，增强领域泛化中的正则化效果，在多个基准上超越现有 DG 方法。
摘要：
领域泛化（DG）旨在从多个已观测的源领域中学习一个通用模型，使其无需进一步训练即可良好地泛化到任意未见的目标领域。DG 的主要挑战在于，由于源领域与目标领域之间存在领域差距，模型不可避免地面临严重的过拟合问题。为缓解该问题，一些基于 dropout 的方法被提出，通过丢弃中间层部分表示来抵抗过拟合。然而，我们观察到这些方法大多只在某些特定层执行 dropout 操作，导致对模型的正则化效果不足。我们认为，在多个层上应用 dropout 可以产生更强的正则化效果，相比以往仅针对特定层的 dropout 方法，能够更充分地缓解源领域上的过拟合问题。本文提出了一种新颖的面向 DG 的逐层逐通道 dropout 方法，该方法随机选择一个层，再随机选择该层中的通道进行 dropout。特别地，所提方法能够生成多种数据变体，从而更好地应对过拟合问题。我们还为所提出的 dropout 方法提供了理论分析，并证明其能够有效降低泛化误差界。此外，我们利用渐进式方案，随着训练进程逐步提高 dropout 比率，从而逐渐增加模型训练难度以增强其鲁棒性。在三个标准基准数据集上的大量实验表明，我们的方法优于多种最先进的 DG 方法。代码可在 https://github.com/lingeringlight/PLACEdropout 获取。
英文摘要：
Domain generalization (DG) aims to learn a generic model from multiple observed source domains that generalizes well to arbitrary unseen target domains without further training. The major challenge in DG is that the model inevitably faces a severe overfitting issue due to the domain gap between source and target domains. To mitigate this problem, some dropout-based methods have been proposed to resist overfitting by discarding part of the representation of the intermediate layers. However, we observe that most of these methods only conduct the dropout operation in some specific layers, leading to an insufficient regularization effect on the model. We argue that applying dropout at multiple layers can produce stronger regularization effects, which could alleviate the overfitting problem on source domains more adequately than previous layer-specific dropout methods. In this paper, we develop a novel layer-wise and channel-wise dropout for DG, which randomly selects one layer and then randomly selects its channels to conduct dropout. Particularly, the proposed method can generate a variety of data variants to better deal with the overfitting issue. We also provide theoretical analysis for our dropout method and prove that it can effectively reduce the generalization error bound. Besides, we leverage the progressive scheme to increase the dropout ratio with the training progress, which can gradually boost the difficulty of training the model to enhance its robustness. Extensive experiments on three standard benchmark datasets have demonstrated that our method outperforms several state-of-the-art DG methods. Our code is available at https://github.com/lingeringlight/PLACEdropout.
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。
