With the rapid development of deep learning technology, a variety of network models for classification have been proposed, which is beneficial to the realization of intelligent waste classification. However, there are still some problems with the existing models in waste classification such as low classification accuracy or long running time. Aimed at solving these problems, in this paper, a waste classification method based on a multilayer hybrid convolution neural network (MLH-CNN) is proposed. The network structure of this method is similar to VggNet but simpler, with fewer parameters and a higher classification accuracy. By changing the number of network modules and channels, the performance of the proposed model is improved. Finally, this paper finds the appropriate parameters for waste image classification and chooses the optimal model as the final model. The experimental results show that, compared with some recent works, the proposed method has a simpler network structure and higher waste classification accuracy. A large number of experiments in a TrashNet dataset show that the proposed method achieves a classification accuracy of up to 92.6%, which is 4.18% and 4.6% higher than that of some state-of-the-art methods, and proves the effectiveness of the proposed method.

Convolutional neural networks (CNNs) have outstanding advantages in the classification of remote sensing scenes. Deep CNN models with better classification performance typically have high complexity, while shallow CNN models with low complexity rarely achieve good classification performance for remote sensing images with complex spatial structures. In this paper, we proposed a new lightweight CNN classification method based on branch feature fusion (LCNN-BFF) for remote sensing scene classification. In contrast to a conventional single linear convolution structure, the proposed model had a bilinear feature extraction structure. The branch feature fusion (BFF) method was utilized to fuse the feature information extracted from the two branches, which improved the classification accuracy. In addition, combining depthwise separable convolution (DSC) and conventional convolution (CConv) to extract image features greatly reduced the complexity of the model on the premise of ensuring the accuracy of classification. We tested the method on four standard data sets. The experimental results showed that, compared with recent classification methods, the number of weight parameters of the proposed method only accounted for less than 5% of the other methods; however, the classification accuracy was equivalent to or even superior to certain high-performance classification methods.

This paper proposes a new method based on a multiple branch cross-connected convolutional neural network (MBCC-CNN) for facial expression recognition. Compared with traditional machine learning methods, the proposed method can extract image features more effectively. In addition, in contrast to single-structure convolutional neural networks, the MBCC-CNN model is constructed based on the residual connection, Network in Network, and tree structure approaches together. It also adds a shortcut cross connection for the summation of the convolution output layer, which makes the data flow between networks more smooth, improves the feature extraction ability of each receptive field. The proposed method can fuse the features of each branches more effectively, which solves the problem of insufficient feature extraction of each branches and increases the recognition performance. The experimental results based on the Fer2013, CK+, FER+ and RAF data sets show that the recognition rates of the proposed MBCC-CNN method are 71.52%, 98.48%, 88.10% and 87.34%, respectively. Compared with some most recently work, the proposed method can provide better facial expression recognition performance and has good robustness. The python code can be download from https://github.com/scp19801980/Facial-expression-recognition .

Due to the lack of data available for training, deep learning hardly performed well in the field of garbage image classification. We choose the TrashNet data set which is widely used in the field of garbage image classification, and try to overcome data deficiencies in this field by optimizing the network structure. In this paper, it is found that the deeper network and short-circuit connection, which are generally accepted in the field of deep learning, will not work well on the TrashNet data set. By analyzing and modifying the network structure, we propose an effective method to improve the network performance on TrashNet data set. This method widens the network by expanding branches, and then uses add layers to realize the fusion of feature information. It can make full use of feature information at slight additional computational cost. Using this method to replace the core structure of the Xception network, the performance of the improved network has been improved greatly. Finally, the M-b Xception network proposed by us achieves 94.34% classification accuracy on the TrashNet data set, and has certain advantages over some state-of-the-art methods on multiple indicators. The python code can be download from https://github.com/scp19801980/Trash-classify-M_b-Xception.

In recent years, convolution neural networks (CNNs) have been widely used in the field of remote sensing scene image classification. However, CNN models with good classification performance tend to have high complexity, and CNN models with low complexity are difficult to obtain high classification accuracy. These models hardly achieve a good trade-off between classification accuracy and model complexity. To solve this problem, we made the following three improvements and proposed a lightweight modular network model. First, we proposed a lightweight self-compensated convolution (SCC). Although traditional convolution can effectively extract features from the input feature map, when there are a large number of filters (such as 512 or 1024 common filters), this process takes a long time. To speed up the network without increasing the computational load, we proposed a self-compensated convolution. The core idea of this convolution is to perform traditional convolution by reducing the number of filters, and then compensate the convoluted channels by input features. It incorporates shallow features into the deep and complex features, which helps to improve the speed and classification accuracy of the model. In addition, we proposed a self-compensating bottleneck module (SCBM) based on the self-compensating convolution. The wider channel shortcut in this module facilitates more shallow information to be transferred to the deeper layer and improves the feature extraction ability of the model. Finally, we used the proposed self-compensation bottleneck module to construct a lightweight and modular self-compensation convolution neural network (SCCNN) for remote sensing scene image classification. The network is built by reusing bottleneck modules with the same structure. A lot of experiments were carried out on six open and challenging remote sensing image scene datasets. The experimental results show that the classification performance of the proposed method is superior to some of the state-of-the-art classification methods with less parameters.

In recent years, with the rapid development of computer vision, increasing attention has been paid to remote sensing image scene classification. To improve the classification performance, many studies have increased the depth of convolutional neural networks (CNNs) and expanded the width of the network to extract more deep features, thereby increasing the complexity of the model. To solve this problem, in this paper, we propose a lightweight convolutional neural network based on attention-oriented multi-branch feature fusion (AMB-CNN) for remote sensing image scene classification. Firstly, we propose two convolution combination modules for feature extraction, through which the deep features of images can be fully extracted with multi convolution cooperation. Then, the weights of the feature are calculated, and the extracted deep features are sent to the attention mechanism for further feature extraction. Next, all of the extracted features are fused by multiple branches. Finally, depth separable convolution and asymmetric convolution are implemented to greatly reduce the number of parameters. The experimental results show that, compared with some state-of-the-art methods, the proposed method still has a great advantage in classification accuracy with very few parameters.