MFVT: Multilevel Feature Fusion Vision Transformer and RAMix Data Augmentation for Fine-Grained Visual Categorization

Author:

Lv Xinyao,Xia Hao,Li Na,Li Xudong,Lan Ruoming

Abstract

The introduction and application of the Vision Transformer (ViT) has promoted the development of fine-grained visual categorization (FGVC). However, there are some problems when directly applying ViT to FGVC tasks. ViT only classifies using the class token in the last layer, ignoring the local and low-level features necessary for FGVC. We propose a ViT-based multilevel feature fusion transformer (MFVT) for FGVC tasks. In this framework, with reference to ViT, the backbone network adopts 12 layers of Transformer blocks, divides it into four stages, and adds multilevel feature fusion (MFF) between Transformer layers. We also design RAMix, a CutMix-based data augmentation strategy that uses the resize strategy for crop-paste images and label assignment based on attention. Experiments on the CUB-200-2011, Stanford Dogs, and iNaturalist 2017 datasets gave competitive results, especially on the challenging iNaturalist 2017, with an accuracy rate of 72.6%.

Funder

Natural Science Foundation of Shandong Province

Shandong Provincial Key Laboratory of Medical Physics and Image Processing Technology

Publisher

MDPI AG

Subject

Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering

Reference32 articles.

1. Ge, W., Lin, X., and Yu, Y. Weakly supervised complementary parts models for fine-grained image classification from the bottom up. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

2. Classification of mammogram images using multiscale all convolutional neural network (MA-CNN);Agnes;J. Med. Syst.,2020

3. Du, R., Chang, D., Bhunia, A.K., Xie, J., Ma, Z., Song, Y.-Z., and Guo, J. Fine-grained visual classification via progressive multi-granularity training of jigsaw patches. Proceedings of the European Conference on Computer Vision.

4. Fine-grained visual classification with multi-scale features based on self-supervised attention filtering mechanism;Chen;Appl. Intell.,2022

5. Fu, J., Zheng, H., and Mei, T. Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3