Fine-Grained Domain Generalization with Feature Structuralization

TL;DR

This paper introduces a Feature Structuralized Domain Generalization (FSDG) model that disentangles features into common, specific, and confounding parts to improve fine-grained domain generalization, inspired by human multi-granularity knowledge.

Contribution

The paper proposes a novel feature structuralization approach with joint optimization constraints, enhancing subtle category distinctions and outperforming state-of-the-art methods in FGDG tasks.

Findings

FSDG achieves an average of 6.2% performance improvement over existing methods.

Extensive experiments validate the effectiveness of feature structuralization.

Explainability analysis confirms the alignment of features with semantic concepts.

Abstract

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.