Multi-branch Recurrent Attention Convolutional Neural Network with Evidence Theory for Fine-Grained Image Classification

2021 ◽  
pp. 177-184
Author(s):  
Zhikang Xu ◽  
Bofeng Zhang ◽  
Haijie Fu ◽  
Xiaodong Yue ◽  
Ying Lv
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Evidence Theory ◽  
Fine Grained

scholarly journals A Unified Matrix-Based Convolutional Neural Network for Fine-Grained Image Classification of Wheat Leaf Diseases

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 11570-11590 ◽  
Author(s):  
Zhongqi Lin ◽  
Shaomin Mu ◽  
Feng Huang ◽  
Khattak Abdul Mateen ◽  
Minjuan Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Fine Grained ◽  
Wheat Leaf

scholarly journals Local Importance Representation Convolutional Neural Network for Fine-Grained Image Classification

Symmetry ◽  
2018 ◽  
Vol 10 (10) ◽  
pp. 479 ◽  
Author(s):  
Yadong Yang ◽  
Xiaofeng Wang ◽  
Hengzheng Zhang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Real Life ◽  
Feature Learning ◽  
Local Area ◽  
Fine Grained ◽  
Benchmark Datasets ◽  
Classification Tasks ◽  
To Receive

Compared with ordinary image classification tasks, fine-grained image classification is closer to real-life scenes. Its key point is how to find the local areas with sufficient discrimination and perform effective feature learning. Based on a bilinear convolutional neural network (B-CNN), this paper designs a local importance representation convolutional neural network (LIR-CNN) model, which can be divided into three parts. Firstly, the super-pixel segmentation convolution method is used for the input layer of the model. It allows the model to receive images of different sizes and fully considers the complex geometric deformation of the images. Then, we replaced the standard convolution of B-CNN with the proposed local importance representation convolution. It can score each local area of the image using learning to distinguish their importance. Finally, channelwise convolution is proposed and it plays an important role in balancing lightweight network and classification accuracy. Experimental results on the benchmark datasets (e.g., CUB-200-2011, FGVC-Aircraft, and Stanford Cars) showed that the LIR-CNN model had good performance in fine-grained image classification tasks.

Sign in / Sign up

Export Citation Format

Share Document