• Home
  • Search
  • Multi-Axis Attention Network using MaxViT for Fine-Grained Image Classification and Discriminative Feature Learning
  • https://doi.org/10.52783/tjjpt.v46.i03.9765Copy DOI Icon

Multi-Axis Attention Network using MaxViT for Fine-Grained Image Classification and Discriminative Feature Learning

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Fine-grained visual categorization (FGVC) is a challenging task in computer vision, which involves discrimination between visually similar subcategories of a big object class. The challenge is further exacerbated in the case of bird species classification, where inter-class variation is subtle and spatially localized, while huge intra-class variation arises due to pose, lighting, and background variations. To address these challenges, we propose the weakly supervised and unified approach Multi-Axis Attention Network with MaxViT for Fine-Grained Image Classification and Discriminative Feature Learning. Our method capitalizes on the strength of the Multi-Axis Vision Transformer (MaxViT), which utilizes convolutional encoding with axial and block-wise self-attention. The combined attention pattern enables the model to capture both local texture information and global contextual information necessary for fine-grained classification. Our model, unlike conventional methods based on part annotations or region-level supervision, is trained end-to-end with image-level supervision alone. To exhibit the model's predictions and to determine regions liable for classification, we utilize Grad-CAM on the last attention layers. The heatmaps obtained show that the model tends to attend to highly discriminative regions like wing structures, beak shapes, and feather textures, giving strong visual confirmation of the model's decision-making. Our framework is assessed on two benchmark datasets, CUB-200-2011 and NABirds, with 95.1% and 94.2% Top-1 classification accuracy, respectively. These results validate the high effectiveness and interpretability of MaxViT as a backbone for fine-grained visual classification tasks under weak supervision.

Similar Papers
  • Conference Article
  • Citations3

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

  • Oct 12, 2022
  • Yizhou He +2
  • Book Chapter
  • Citations1

Selecting Discriminative Features for Fine-Grained Visual Classification

  • Jan 01, 2020
  • Qin Xu +3
  • PDF
  • Research Article
  • Citations3

Exploiting Category Similarity-Based Distributed Labeling for Fine-Grained Visual Classification

  • Jan 01, 2020
  • IEEE Access
  • Pengzhen Du +3
  • Research Article

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

  • May 26, 2026
  • Journal of Control and Decision
  • Dongpeng Zou +4
  • Conference Article
  • Citations33

GRAD-CAM Guided Channel-Spatial Attention Module for Fine-Grained Visual Classification

  • Oct 25, 2021
  • Shuai Xu +3
  • Research Article
  • Citations5

KFWC: A Knowledge-Driven Deep Learning Model for Fine-grained Classification of Wet-AMD

  • Dec 15, 2022
  • Computer Methods and Programs in Biomedicine
  • Haihong E +8
  • 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
  • PDF
  • Research Article
  • Citations4

Remote Sensing Image Harmonization Method for Fine-Grained Ship Classification

  • Jun 17, 2024
  • Remote Sensing
  • Jingpu Zhang +4
  • Research Article
  • Citations1

MCM-ViT:Mask-guided context-enhanced multi-scale transformer for fine-grained visual classification

  • Dec 04, 2024
  • Computers and Electrical Engineering
  • Bicheng Li +5
  • Research Article
  • Citations15

Fine-grained visual classification via multilayer bilinear pooling with object localization

  • Jan 09, 2021
  • The Visual Computer
  • Ming Li +4
  • Conference Article
  • Citations13

Learning Hierarchal Channel Attention for Fine-grained Visual Classification

  • Oct 17, 2021
  • Xiang Guan +3
  • Conference Article
  • Citations3

Augmenting descriptors for fine-grained visual categorization using polynomial embedding

  • Jul 01, 2013
  • Hideki Nakayama
  • 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
  • Citations83

AA-trans: Core attention aggregating transformer with information entropy selector for fine-grained visual classification

  • Mar 21, 2023
  • Pattern Recognition
  • Qi Wang +5
  • Conference Article
  • Citations4

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

  • Dec 01, 2019
  • Cong Zou +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.