Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference

Recently, causal models have gained significant attention in natural language processing (NLP) and computer vision (CV) due to their capability of capturing features with causal relationships. This study addresses Fine-Grained Visual Categorization (FGVC) by incorporating high-order feature fusions...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhang Zhang, Yuan Wan, Jiahui Hao, Zaili Yang, Huanhuan Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/8/1340
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, causal models have gained significant attention in natural language processing (NLP) and computer vision (CV) due to their capability of capturing features with causal relationships. This study addresses Fine-Grained Visual Categorization (FGVC) by incorporating high-order feature fusions to improve the representation of feature interactions while mitigating the influence of confounding factors through causal inference. A novel high-order feature learning framework with causal inference is developed to enhance FGVC. A causal graph tailored to FGVC is constructed, and the causal assumptions of baseline models are analyzed to identify confounding factors. A reconstructed causal structure establishes meaningful interactions between individual images and image pairs. Causal interventions are applied by severing specific causal links, effectively reducing confounding effects and enhancing model robustness. The framework combines high-order feature fusion with interventional fine-grained learning by performing causal interventions on both classifiers and categories. The experimental results demonstrate that the proposed method achieves accuracies of 90.7% on CUB-200, 92.0% on FGVC-Aircraft, and 94.8% on Stanford Cars, highlighting its effectiveness and robustness across these widely used fine-grained recognition datasets. Comprehensive evaluations of these three widely used fine-grained recognition datasets demonstrate the proposed framework’s effectiveness and robustness.
ISSN:2227-7390