Two‐Stage Feature Selection for Fine‐Grained Image Recognition Via Partial Order Analysis and Heterogeneity Evaluation
Authors:
Open Access
- 1 January 2025
- journal article
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Abstract
The core challenge of fine‐grained image recognition (FGIR) tasks is distinguishing highly similar subclasses within the same base category. Most CNN‐based deep learning methods typically focus on extracting information from local regions while overlook the inherent structure between subclasses and the complex relationships between features. This paper presents a two‐stage feature selection method based on partial order analysis (POA) and heterogeneity evaluation (HE) for FGIR tasks, guiding the model to focus on distinctive features while reducing uncertainty caused by interfering information. Specifically, in the POA stage, clustering first groups similar subcategories into a medium‐granularity category. Formal concept analysis then models their hierarchical partial order, identifying “shared features” among subcategories and “exclusive features” unique to each. This structured representation highlights key contrastive cues. In the HE stage, a novel heterogeneity index is introduced to measure the fluctuation of low‐level features within each fine‐grained category. This index guides the model to suppress pseudo‐discriminative features with high heterogeneity, mitigating the impact of noisy and unstable information on decision‐making. We perform comprehensive experiments on three commonly used benchmark datasets (CUB‐200‐2011, Stanford Cars, and FGVC‐Aircraft). Experimental results show that the proposed method outperforms classic FGIC methods, validating the effectiveness of our approach.Keywords
Funding Information
- Natural Science Foundation of Shanxi Province (202403021221143)
- National Natural Science Foundation of China (62273248)
This publication has 49 references indexed in Scilit:
- Data complexity: An FCA-based approachInternational Journal of Approximate Reasoning, 2023
- Feature relocation network for fine-grained image classificationNeural Networks, 2023
- A user-guided reduction concept lattice and its algebraic structureExpert Systems with Applications, 2023
- Graph neural networks induced by concept lattices for classificationInternational Journal of Approximate Reasoning, 2023
- A novel part-level feature extraction method for fine-grained vehicle recognitionPattern Recognition, 2022
- Learning sequentially diversified representations for fine-grained categorizationPattern Recognition, 2022
- Fine-Grained Visual Classification via Progressive Multi-granularity Training of Jigsaw Patches2020
- Attribute hierarchy based multi-task learning for fine-grained image classificationNeurocomputing, 2020
- Which and How Many Regions to Gaze: Focus Discriminative Regions for Fine-Grained Visual CategorizationInternational Journal of Computer Vision, 2019
- RESTRUCTURING LATTICE THEORY: AN APPROACH BASED ON HIERARCHIES OF CONCEPTS2009