PPANet: Point-Wise Pyramid Attention Network for Semantic Segmentation
| Autor: | Chenxi Huang, Jane Yang, Chenhui Yang, Xingcong Yao, YuXuan Chen, Yunyi Chen, Mohammed A. M. Elhassan, Yinuo Cheng |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Technology
Article Subject Computer Networks and Communications Computer science Advanced driver assistance systems 02 engineering and technology TK5101-6720 Convolutional neural network Upsampling Encoding (memory) 0502 economics and business 0202 electrical engineering electronic engineering information engineering Computer vision Segmentation Pyramid (image processing) Electrical and Electronic Engineering 050210 logistics & transportation business.industry 05 social sciences Feature (computer vision) Telecommunication 020201 artificial intelligence & image processing Artificial intelligence business Encoder Information Systems |
| Zdroj: | Wireless Communications and Mobile Computing, Vol 2021 (2021) |
| ISSN: | 1530-8669 |
| DOI: | 10.1155/2021/5563875 |
| Popis: | In recent years, convolutional neural networks (CNNs) have been at the centre of the advances and progress of advanced driver assistance systems and autonomous driving. This paper presents a point-wise pyramid attention network, namely, PPANet, which employs an encoder-decoder approach for semantic segmentation. Specifically, the encoder adopts a novel squeeze nonbottleneck module as a base module to extract feature representations, where squeeze and expansion are utilized to obtain high segmentation accuracy. An upsampling module is designed to work as a decoder; its purpose is to recover the lost pixel-wise representations from the encoding part. The middle part consists of two parts point-wise pyramid attention (PPA) module and an attention-like module connected in parallel. The PPA module is proposed to utilize contextual information effectively. Furthermore, we developed a combined loss function from dice loss and binary cross-entropy to improve accuracy and get faster training convergence in KITTI road segmentation. The paper conducted the training and testing experiments on KITTI road segmentation and Camvid datasets, and the evaluation results show that the proposed method proved its effectiveness in road semantic segmentation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text