• Home
  • Search
  • WaveFormer: a transformer with wavelet fusion for fine-grained visual classification
  • https://doi.org/10.1080/23307706.2026.2640556Copy DOI Icon

WaveFormer: a transformer with wavelet fusion for fine-grained visual classification

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Fine-grained visual classification (FGVC) is a challenging task that requires distinguishing highly similar categories with subtle inter-class differences while accommodating significant intra-class variations. While Vision Transformers excel at many vision tasks due to their powerful global modelling, their performance in fine-grained classification is hindered by a difficulty in capturing subtle local details and fusing information across multiple scales. To address these shortcomings, we propose WaveFormer, a novel transformer framework that incorporates wavelet transformations into the ViT architecture to enhance multi-scale feature extraction and global-local information fusion. By leveraging frequency-domain analysis, WaveFormer enhances computational efficiency, feature fidelity, and interpretability, effectively tackling critical challenges in fine-grained classification. WaveFormer achieves state-of-the-art performance on the enhanced Fish4Knowledge dataset, outperforming mainstream architectures like Swin Transformer with significantly reduced FLOPs and superior statistical stability validated across multiple random seeds. This demonstrates the value of frequency-domain integration in deep learning for advancing FGVC and other detail-oriented tasks.

Similar Papers
  • Conference Article
  • Citations3

Weakly-supervised attention mechanism via score-CAM for fine-grained visual classification

  • Oct 12, 2022
  • Yizhou He +2
  • Conference Article
  • Citations4

Weighted Focus-Attention Deep Network for Fine-grained Image Classification

  • Dec 01, 2019
  • Cong Zou +3
  • Conference Article

Denoising Labels: A Noise-robust Method for Webly-supervised Fine-grained Visual Classification

  • Sep 26, 2022
  • Dan Huang +1
  • Research Article
  • Citations24

Exploration of Class Center for Fine-Grained Visual Classification

  • Oct 01, 2024
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Hang Yao +6
  • Research Article
  • Citations2

Learning multi-scale attention network for fine-grained visual classification

  • May 01, 2025
  • Journal of Information and Intelligence
  • Peipei Zhao +6
  • Research Article
  • Citations6

MSFF: Multi-Scale feature fusion for fine-grained image classification

  • Jan 01, 2023
  • Academic Journal of Computing & Information Science
  • Yabo Shang +1
  • Conference Article
  • Citations4

Attention-based Multi-scale ViT Fine-grained Visual Classification

  • Dec 09, 2022
  • Rujia Li +4
  • Research Article
  • Citations4

Holistic fine-grained global glomerulosclerosis characterization: from detection to unbalanced classification.

  • Feb 17, 2022
  • Journal of Medical Imaging
  • Yuzhe Lu +7
  • Research Article
  • Citations42

Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification.

  • Jan 01, 2024
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Jiahui Wang +4
  • Research Article
  • Citations9

Shape-aware fine-grained classification of erythroid cells

  • Feb 21, 2023
  • Applied Intelligence
  • Ye Wang +6
  • Conference Article
  • Citations1

AFG-Net: a fine-grained classification network for aircrafts in remote sensing images based on improved ConvNext

  • Jul 19, 2024
  • Ruofei Ma +4
  • Research Article

UB-Former: A fine-grained classification method for images of insects using biomorphic features.

  • Oct 01, 2025
  • Computational biology and chemistry
  • Shilu Kang +3
  • Research Article
  • Citations1

Deep learning for fine-grained molecular-based colorectal cancer classification.

  • Jan 01, 2023
  • Translational cancer research
  • Junyu Bian +3
  • Conference Article

A Deformable Convolutional Neural Network with Oriented Response for Fine-Grained Visual Classification

  • Feb 26, 2021
  • Shangxian Ruan +2
  • Research Article
  • Citations80

Sewer pipe defect detection via deep learning with local and global feature fusion

  • Jul 07, 2021
  • Automation in Construction
  • Dawei Li +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.