通过双曲空间幻觉提升细粒度域泛化能力，增强对细微特征的鲁棒性。
Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination
- 用双曲空间建模高阶统计，显式分离风格变化与细粒度特征
- 在三个基准上达到当前最优性能，显著提升未见域上的泛化能力
- 适合研究细粒度识别与域泛化交叉问题的学者使用
细粒度域泛化（FGDG）旨在仅基于源域数据训练时，学习出能在未见目标域中良好泛化的细粒度表示。相比通用域泛化，FGDG更具挑战性，因细粒度类别依赖于细微、隐蔽的模式，而这些模式在光照、色彩等跨域风格变化下极易失真。为此，本文提出一种新型双曲状态空间幻觉（HSSH）方法，包含两个关键组件：状态空间幻觉（SSH）与双曲流形一致性（HMC）。SSH首先外推并幻觉化源图像，以丰富状态嵌入的风格多样性；随后，幻觉前后的状态嵌入被投影至双曲流形。该流形可建模高阶统计特性，从而更优地区分细粒度模式。最终通过最小化双曲距离，消除风格变化对细粒度特征的影响。在三个FGDG基准上的实验表明，该方法性能达到当前最优。
原文摘要 · Abstract (English)
Fine-grained domain generalization (FGDG) aims to learn a fine-grained representation that can be well generalized to unseen target domains when only trained on the source domain data. Compared with generic domain generalization, FGDG is particularly challenging in that the fine-grained category can be only discerned by some subtle and tiny patterns. Such patterns are particularly fragile under the cross-domain style shifts caused by illumination, color and etc. To push this frontier, this paper presents a novel Hyperbolic State Space Hallucination (HSSH) method. It consists of two key components, namely, state space hallucination (SSH) and hyperbolic manifold consistency (HMC). SSH enriches the style diversity for the state embeddings by firstly extrapolating and then hallucinating the source images. Then, the pre- and post- style hallucinate state embeddings are projected into the hyperbolic manifold. The hyperbolic state space models the high-order statistics, and allows a better discernment of the fine-grained patterns. Finally, the hyperbolic distance is minimized, so that the impact of style variation on fine-grained patterns can be eliminated. Experiments on three FGDG benchmarks demonstrate its state-of-the-art performance.
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。