CVApr 18, 2025

Cross-Hierarchical Bidirectional Consistency Learning for Fine-Grained Visual Classification

arXiv:2504.13608v12 citationsh-index: 7Inf Sci
Originality Incremental advance
AI Analysis

This addresses the challenge of classifying closely related subcategories in computer vision, representing an incremental improvement over existing methods.

The paper tackles fine-grained visual classification by leveraging tree hierarchies to improve accuracy and consistency, achieving state-of-the-art results on three benchmark datasets.

Fine-Grained Visual Classification (FGVC) aims to categorize closely related subclasses, a task complicated by minimal inter-class differences and significant intra-class variance. Existing methods often rely on additional annotations for image classification, overlooking the valuable information embedded in Tree Hierarchies that depict hierarchical label relationships. To leverage this knowledge to improve classification accuracy and consistency, we propose a novel Cross-Hierarchical Bidirectional Consistency Learning (CHBC) framework. The CHBC framework extracts discriminative features across various hierarchies using a specially designed module to decompose and enhance attention masks and features. We employ bidirectional consistency loss to regulate the classification outcomes across different hierarchies, ensuring label prediction consistency and reducing misclassification. Experiments on three widely used FGVC datasets validate the effectiveness of the CHBC framework. Ablation studies further investigate the application strategies of feature enhancement and consistency constraints, underscoring the significant contributions of the proposed modules.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes