DomainDrop：抑制域敏感通道以实现域泛化
DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization
AI总结：
针对深度神经网络因域偏移在未见测试集上性能下降的问题，提出DomainDrop框架，通过域判别器识别并丢弃特征图中的不稳定通道以增强通道鲁棒性，理论证明可降低泛化界，多基准实验达SOTA性能。
摘要：
深度神经网络已在各类视觉任务中展现出显著成效。然而，当应用于未见过的测试数据集时，当前最优模型往往会因域偏移而出现性能下降。本文从增强特征图中通道对域偏移的鲁棒性这一全新视角，提出了一种域泛化新方法。我们观察到，在源域上训练的模型包含大量通道，这些通道在不同域间的激活表现不稳定，它们倾向于捕捉域特定特征，且在面对未见过的目标域时会表现异常。为解决该问题，我们提出DomainDrop框架以持续提升通道对域偏移的鲁棒性，该框架在正向传播过程中，利用域判别器识别并丢弃每一层网络特征图中的不稳定通道。我们从理论上证明了该框架能够有效降低泛化界。在多个基准上开展的大量实验表明，与其他同类方法相比，本框架取得了当前最优性能。我们的代码可在https://github.com/lingeringlight/DomainDrop获取。
英文摘要：
Deep Neural Networks have exhibited considerable success in various visual tasks. However, when applied to unseen test datasets, state-of-the-art models often suffer performance degradation due to domain shifts. In this paper, we introduce a novel approach for domain generalization from a novel perspective of enhancing the robustness of channels in feature maps to domain shifts. We observe that models trained on source domains contain a substantial number of channels that exhibit unstable activations across different domains, which are inclined to capture domain-specific features and behave abnormally when exposed to unseen target domains. To address the issue, we propose a DomainDrop framework to continuously enhance the channel robustness to domain shifts, where a domain discriminator is used to identify and drop unstable channels in feature maps of each network layer during forward propagation. We theoretically prove that our framework could effectively lower the generalization bound. Extensive experiments on several benchmarks indicate that our framework achieves state-of-the-art performance compared to other competing methods. Our code is available at https://github.com/lingeringlight/DomainDrop.
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。
