细粒度域泛化与特征结构化
Fine-Grained Domain Generalization with Feature Structuralization
AI总结：
针对细粒度域泛化中细微特征易受域分布变化影响的问题，提出特征结构化域泛化模型，通过解纠缠特征为共同、特定和混淆部分并联合优化五个约束，在三个基准上平均提升6.2%性能。
摘要：
细粒度域泛化（FGDG）是一项比传统域泛化（DG）任务更具挑战性的任务，原因在于其类别间差异小、类别内差异相对较大。当域分布发生变化时，细微特征的脆弱性会导致模型性能严重下降。然而，人类天生具备利用从类别中辨别共性和特异性而涌现的结构化多粒度知识，对分布外数据进行泛化的能力。同样，我们提出了一种特征结构化域泛化（FSDG）模型，其中特征被结构化为共同、特定和混淆部分，并与其相关的语义概念和谐对齐，以提升FGDG的性能。具体而言，特征结构化（FS）是通过五个约束的联合优化实现的：一个应用于解纠缠部分的去相关函数，三个确保共同特征一致性和特定特征独特性的约束，以及一个预测校准项。通过施加这些规定，FSDG被促使基于多粒度知识对特征进行解纠缠和对齐，从而促进类别间稳健的细微区分。在三个基准上进行的大量实验一致验证了FSDG相对于最先进方法的优越性，在FGDG性能上平均提高了6.2%。此外，对类别间共享概念与模型通道之间显式概念匹配强度的可解释性分析，以及在各种主流模型架构上的实验，证实了FS的有效性。
英文摘要：
Fine-grained domain generalization (FGDG) is a more challenging task than traditional DG tasks due to its small inter-class variations and relatively large intra-class disparities. When domain distribution changes, the vulnerability of subtle features leads to a severe deterioration in model performance. Nevertheless, humans inherently demonstrate the capacity for generalizing to out-of-distribution data, leveraging structured multi-granularity knowledge that emerges from discerning the commonality and specificity within categories. Likewise, we propose a Feature Structuralized Domain Generalization (FSDG) model, wherein features experience structuralization into common, specific, and confounding segments, harmoniously aligned with their relevant semantic concepts, to elevate performance in FGDG. Specifically, feature structuralization (FS) is accomplished through joint optimization of five constraints: a decorrelation function applied to disentangled segments, three constraints ensuring common feature consistency and specific feature distinctiveness, and a prediction calibration term. By imposing these stipulations, FSDG is prompted to disentangle and align features based on multi-granularity knowledge, facilitating robust subtle distinctions among categories. Extensive experimentation on three benchmarks consistently validates the superiority of FSDG over state-of-the-art counterparts, with an average improvement of 6.2% in FGDG performance. Beyond that, the explainability analysis on explicit concept matching intensity between the shared concepts among categories and the model channels, along with experiments on various mainstream model architectures, substantiates the validity of FS.
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。
