Fine-Grained Image Classification Based on Multi-Scale Feature Fusion

Table 1. Classification accuracy of different components%
View table
Table 1. Classification accuracy of different components%
Dataset Resnet101 Resnet101+FPN(featurepyramidnetworks) Resnet101+FPN+objectfilter
CUB-200-2011 81.4 83.4 85.7
Stanford Dogs 77.5 81.3 83.5

Table 2. Classification accuracy for different numbers of small target areas%
View table
Table 2. Classification accuracy for different numbers of small target areas%
Dataset Two areas Three areas Four areas
CUB-200-2011 83.6 85.7 86.0
Stanford Dogs 80.9 83.5 84.0

Table 3. Comparison of classification accuracy of different algorithms for Stanford Dogs dataset
View table
Table 3. Comparison of classification accuracy of different algorithms for Stanford Dogs dataset
Reference Method Accuracy /%
Ref. [10] Pyramid matching 80.4
Ref. [8] DVAN 81.5
Ref. [9] RACNN 87.3
This papar Multi-scale feature fusion 83.5

Table 4. Comparison of classification accuracy of different algorithms for CUB-200-2011 dataset
View table
Table 4. Comparison of classification accuracy of different algorithms for CUB-200-2011 dataset
Reference Method Accuracy /%
Ref. [11] Part-RCNN 81.6
Ref. [14] B-CNN 84.1
Ref. [7] PDFR (picking deepfilter responses) 84.5
Ref. [9] RACNN 85.3
This papar Multi-scale feature fusion 85.7

Tools

Get Citation

Copy Citation Text

Siyao Li, Yuhong Liu, Rongfen Zhang. Fine-Grained Image Classification Based on Multi-Scale Feature Fusion[J]. Laser & Optoelectronics Progress, 2020, 57(12): 121002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Sep. 26, 2019

Accepted: Dec. 11, 2019

Published Online: Jun. 3, 2020

The Author Email: Zhang Rongfen (rfzhang@gzu.edu.cn)

DOI:10.3788/LOP57.121002

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Classification accuracy of different components%

Table 1. Classification accuracy of different components%

Table 2. Classification accuracy for different numbers of small target areas%

Table 2. Classification accuracy for different numbers of small target areas%

Table 3. Comparison of classification accuracy of different algorithms for Stanford Dogs dataset

Table 3. Comparison of classification accuracy of different algorithms for Stanford Dogs dataset

Table 4. Comparison of classification accuracy of different algorithms for CUB-200-2011 dataset

Table 4. Comparison of classification accuracy of different algorithms for CUB-200-2011 dataset