Skip to content
Conference

MASF-Net: efficient linear attention guided few-shot fine-grained image recognition

Aug 2026 · International Conference on Digital Image Processing · Vol 14351, pp. 143512I - 143512I-14 · 0 citations · 19 references
Engineering

TL;DR

Extensive experiments on three challenging fine-grained benchmarks demonstrate that MASFNet consistently outperforms state-of-the-art methods in both 5-way 1-shot and 5-way 5-shot settings.

Abstract

Few-shot fine-grained image classification (FS-FGIC) aims to distinguish visually similar subcategories with only a handful of labeled examples, posing significant challenges due to subtle inter-class differences and large intra-class variations. Existing methods often fail to fully leverage complementary information from different network hierarchies or lack efficient mechanisms to focus on discriminative regions. To address these issues, we propose a novel Multi-scale Attention-based Similarity Fusion Network (MASF-Net). Our approach introduces three key components: (1) a Feature Enhancement Transformer (FET) module that performs multi-scale feature extraction and cross-scale interaction via linear attention; (2) a Cross-attention Relation Learner (CRL) module that models fine-grained semantic relationships between support and query sets with an efficient linear attention mechanism; and (3) a Multi-Scale Fusion Classifier (MSFC) module that adaptively integrates multi-level features for final classification. Extensive experiments on three challenging fine-grained benchmarks—CUB-200-2011, Stanford-Dogs, and Stanford-Cars—demonstrate that MASFNet consistently outperforms state-of-the-art methods in both 5-way 1-shot and 5-way 5-shot settings. Visualizations illustrate the model's ability to focus on discriminative regions and establish accurate semantic correspondences.

View source

Similar papers

Open access Aug 2026

Semantic Topological Multi-Scale Part Network for Fine-Grained Visual Classification

A Prior-Guided Part Aggregator (PGA) is designed, which leverages the foreground prior provided by foundation models to guide discriminative part discovery, enhancing target region responses while suppressing background interference, and a Topology-Informed Semantic Graph Convolutional Network (TIS-GCN) is designed to...

Xue-Rong Liu, Min Zhi, Yan-Jun Yin et al. · 0 citations
Sep 2026

Dual-view multi-scale feature enhancement and fusion for fine-grained visual classification

A dual-view multi-scale feature enhancement and fusion network is proposed for accurate and efficient FGVC, designed to strengthen discriminative cues in features through multi-branch modeling and channel attention and to adaptively integrate enhanced multi-level features in both spatial and channel dimensions.

Ke Zhang, Jun-Kai Zhong, Peng Gao et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification

This study introduces a novel plug-and-play amplitude-phase integration module that effectively combines local and global frequency amplitude and phase information for obtaining more comprehensive feature descriptors in few-shot fine-grained image classification.

Rui-Ling Liu, Lin-Yu Zhang, Wen-Yi Zeng et al. · 0 citations
Sep 2026

Multimodal graph-based fusion via image descriptions for few-shot open-set recognition.

A multimodal Graph-based Fusion (MGF) framework that learns visually grounded semantic representations to enhance FSOR performance and achieves superior open-set recognition and competitive closed-set classification performance.

Xilang Huang, Seon-Han Choi · 0 citations
Conference Open access Sep 2026

MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in zero-shot transfer but often struggles with dense prediction tasks due to low spatial resolution and the loss of structural information. To address these limitations, we propose MARS-CLIP (Multi-resolution and Attention Refined S...

Nagito Saito, Shintaro Ito, Koichi Ito et al. · 0 citations
Conference Open access 2026

Progress of fine-grained image classification under weakly supervised paradigm

This paper systematically reviews the development of weakly supervised fine-grained image classification, defines its core concepts and task characteristics, and divides it into traditional machine learning and deep learning stages.

Jiayuan Liu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.