BiSeNet-oriented context attention model for image semantic segmentation

Abstract

When the traditional semantic segmentation model is adopted, the different feature importance of feature maps is ignored in the feature extraction stage, which results in the detail loss, and affects the segmentation effect. In this paper, we propose a BiSeNet-oriented context attention model for image semantic segmentation. In the BiSeNet, the spatial path is utilized to extract more low-level features to solve the problem of information loss in deep network layers. Context attention mechanism is used to mine high-level implied semantic features of images. Mean while, the focus loss is used as the loss function to improve the final segmentation effect by reducing the internal weighting. Finally, we conduct experiments on open data sets, and the results show that pixel accuracy, average pixel accuracy, and aver age Intersection-over-Union are greatly improved compared with other state-of-the art semantic segmentation models. It effectively improves the accuracy of feature extraction, reduces the loss of feature details, and improves the final segmentation effect.

Remote Sensing Image Segmentation Based on a Novel Gaussian Mixture Model and SURF Algorithm

“…Image segmentation is an important stage in image processing, which has been widely used in the fields of image recognition, 3D reconstruction and target tracking (Hong et al 2021;Teng et al 2022). The areas of interest in the image are called the target or foreground, and the rest are called the background.…”

A Multi-Feature Fusion Model Based on Denoising Convolutional Neural Network and Attention Mechanism for Image Classification

“…(Alex Krizhevsky et al 2017) proposed AlexNetc network, which adopted ReLU activation function and GPU packet convolution for parallel training. (Teng et al 2022) applied batch normalization to neural networks, which ensured that the output distribution of each layer in the network was basically stable. At the same time, the network greatly reduces the dependence on the initial parameters and improves the network performance.…”