In response to the problems of insufficient feature extraction ability of expression recognition models in current research, and the deeper the depth of the model, the more serious the loss of useful information, a residual network model with multi scale convolutional attention is proposed. This ...
One of the earliest and most powerful DL-based convolutional neural network (CNN) models for image classification is residual networks (ResNets)31. In this study, we proposed a model by reformulating the layers as learning residual functions with reference to the layer inputs instead of learning ...
The related work of this study mainly includes three aspects: 1) Convolutional neural network; 2) Large kernel convolution; 3) Variants of Unet network. Method In this section, the structure of the proposed MLKCA-Unet for automatic semantic segmentation in spinal MRI images is described, and th...
researchers have undertaken investigations from various perspectives. The process of feature extraction inevitably leads to information loss24. Extracting and fusing multi-scale hierarchical features can effectively alleviate this problem. By inputting the source image into a convolutional network ...
A spatial-temporal attention-based method and a new dataset for remote sensing image change detection Remote Sens. (2020) Chen, H., Wu, C., Du, B., Zhang, L., 2019a. Deep Siamese multi-scale convolutional network for change detection in... ChenH. et al. Change detection in multisour...
We deployed a U-Net convolutional neural network to map surface water from Sentinel-1 Synthetic Aperture Radar (SAR) data and tested the model performance using different hyperparameter tuning combinations to identify the optimal learning rate and loss function. The performance was then evaluated ...
A novel multiscale dilated convolutional network (MSDC-Net) is proposed against the scale difference of lesions and the low contrast between lesions and normal tissues in CT images. In our MSDC-Net, we propose a multiscale feature capture block (MSFCB) to effectively capture multiscale features...
Specifically, a residual dilated dense module containing dilated dense convolutional layers is employed to enlarge the receptive field of the proposed network. Then, we train such module to learn multi-scale features of images. A feature aggregation module is sequentially designed with dual attention ...
First, methods involving the use of traditional convolutional neural networks mainly focus on local perception domains; they lack global perception and do not assign different weights to different parts of the input. Although an attention mechanism places more emphasis on the global perception domain, ...
With the large amount of high-spatial resolution images now available, scene classification aimed at obtaining high-level semantic concepts has drawn great attention. The convolutional neural networks (CNNs), which are typical deep learning methods, have widely been studied to automatically learn featur...