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

Zhang, Y, Wan, Y, Hao, J, Yang, Z and Li, H (2025) Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference. Mathematics, 13 (8).

[thumbnail of Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference.pdf]
Preview
Text
Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference.pdf - Published Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview

Abstract

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.

Item Type: Article
Uncontrolled Keywords: 49 Mathematical Sciences; Networking and Information Technology R&D (NITRD); Machine Learning and Artificial Intelligence; 2.1 Biological and endogenous factors; 49 Mathematical sciences
Subjects: Q Science > QA Mathematics
Divisions: Engineering
Publisher: MDPI
Date of acceptance: 17 April 2025
Date of first compliant Open Access: 29 May 2025
Date Deposited: 29 May 2025 10:37
Last Modified: 29 May 2025 10:45
DOI or ID number: 10.3390/math13081340
URI: https://researchonline.ljmu.ac.uk/id/eprint/26458
View Item View Item