Triple ANet: Adaptive Abnormal-aware Attention Network for WCE Image Classification

2019 ◽  
pp. 293-301 ◽  
Author(s):  
Xiaoqing Guo ◽  
Yixuan Yuan
Keyword(s):  
Image Classification ◽  
Attention Network

scholarly journals Residual Attention Network for Image Classification

2017 ◽  
Author(s):  
Fei Wang ◽  
Mengqing Jiang ◽  
Chen Qian ◽  
Shuo Yang ◽  
Cheng Li ◽  
...  
Keyword(s):  
Image Classification ◽  
Attention Network

scholarly journals Multi-Label Image Classification by Feature Attention Network

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 98005-98013 ◽  
Author(s):  
Zheng Yan ◽  
Weiwei Liu ◽  
Shiping Wen ◽  
Yin Yang
Keyword(s):  
Image Classification ◽  
Attention Network ◽  
Feature Attention

scholarly journals A 3D-2D Multibranch Feature Fusion and Dense Attention Network for Hyperspectral Image Classification

Micromachines ◽  
2021 ◽  
Vol 12 (10) ◽  
pp. 1271
Author(s):  
Hongmin Gao ◽  
Yiyan Zhang ◽  
Yunfei Zhang ◽  
Zhonghao Chen ◽  
Chenming Li ◽  
...  
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Feature Fusion ◽  
Receptive Fields ◽  
Classification Performance ◽  
Redundant Information ◽  
Hyperspectral Image Classification ◽  
Training Process ◽  
Attention Network ◽  
Spatial Features

In recent years, hyperspectral image classification (HSI) has attracted considerable attention. Various methods based on convolution neural networks have achieved outstanding classification results. However, most of them exited the defects of underutilization of spectral-spatial features, redundant information, and convergence difficulty. To address these problems, a novel 3D-2D multibranch feature fusion and dense attention network are proposed for HSI classification. Specifically, the 3D multibranch feature fusion module integrates multiple receptive fields in spatial and spectral dimensions to obtain shallow features. Then, a 2D densely connected attention module consists of densely connected layers and spatial-channel attention block. The former is used to alleviate the gradient vanishing and enhance the feature reuse during the training process. The latter emphasizes meaningful features and suppresses the interfering information along the two principal dimensions: channel and spatial axes. The experimental results on four benchmark hyperspectral images datasets demonstrate that the model can effectively improve the classification performance with great robustness.

Sign in / Sign up

Export Citation Format

Share Document