Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination
Journal:
arXiv
Published Date:
Apr 10, 2025
Abstract
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.
