.png){kind=icon}
Return
Knowledge-driven prototype refinement for few-shot fine-grained recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2025.113535.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Advancements in deep learning have made image classification rival human performance with sufficient data and supervision. However, in domains with limited visual samples and high labeling costs, enabling AI systems to learn efficiently from few examples is challenging. This challenge is compounded in fine-grained categories, where subtle differences and scarce samples hinder robust representation extraction. To address this, we propose the Knowledge-Driven Prototype Refinement (KDPR) framework, which enhances few-shot finegrained recognition by integrating prior knowledge from text. KDPR simulates human focus on discriminative foreground regions to extract refined views, forming a dual-branch learning framework alongside original images. It also constructs an unsupervised adjacency graph among visual instances and uses graph neural networks to improve category representation robustness. Additionally, a knowledge transfer-based image recognizer integrates prior text embeddings with global semantics directly into visual recognition, providing extra semantic guidance. To optimize knowledge-to-vision mapping, an auxiliary spatial prototype calibration aligns prototype representations across multiple spaces. Extensive experiments on three fine-grained datasets and two popular backbones demonstrate the effectiveness and state-of-the-art performance of our approach, especially in 1-shot learning. The source code is available at: https://github.com/HHU-JialeChen/KDPRNet.
Keywords:
Few-shot learning
Fine-grained recognition
Knowledge transfer
Semantic alignment
Journal
K
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available
Cited Papers
Deep metric learning for few-shot image classification: A Review of recent developments.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSave
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSave
View more