A Novel Multi-Branch Channel Expansion Network for Garbage Image Classification

Abstract

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-theart methods on multiple indicators. The python code can be download from https://github.com/scp19801980/Trash-classify-M_b-Xception.

Efficient Anomaly Detection in Crowd Videos Using Pre-Trained 2D Convolutional Neural Networks

“…Deepening the network is often appropriate in complex scene classification, however, reducing the number of convolution layers also greatly affects the network performance, as previously reported in the literature [45,46]. Therefore, inspired by the work of Shi et al [47], it was deemed worthwhile to explore the relationship between the depth of the network and its performance specific to the current dataset. For this purpose, we preserved the non-core (non-repeating) structure of the network and tried with different network structures within the core part.…”

A Hybrid Deep Learning Model for Trash Classification Based on Deep Trasnsfer Learning

“…Recently, Shi et al [19] proposed a novel network improvement method based on channel expansion for trash image classification which named M-b Xception. e best performance results were 94.34 % on the TrashNet dataset.…”

“…We replicate state-of-the-art models for trash classification including RecycleNet [7], ResNet-50 [11], DNN-TC [17], RexNeXt-101 [18], and M-b Xception [19] to compare with the proposed model. Specifically, we utilized the ResNet-50 model and RecycleNet model with the same configurations, which were described in their work.…”

Take the trash out... to the edge. Creating a Smart Waste Bin based on 5G Multi-access Edge Computing

“…With the success and popularity of machine learning, and in particular of Convolutional Neural Networks (CNN) in the field of computer vision, a considerable amount of works tackle the problem of image-based waste recognition [1,3,13,16]. A common approach is to use already existing CNN models (pre-trained over very large image databases, such as ImageNet [4]), which are known to provide excellent results in terms of image classification (e.g., AlexNet [9] or VGG16 [14]), and fine tune their last layers of the neural network with datasets containing images of pieces of trash 2 .…”