https://scholars.lib.ntu.edu.tw/handle/123456789/638461
標題: | EffSegmentNet: Efficient Design for Real-time Semantic Segmentation | 作者: | Wang, Cyun Bo JIAN-JIUN DING |
公開日期: | 1-一月-2023 | 來源出版物: | 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 | 摘要: | This paper represents the EffSegmentNet, which is a powerful real-time semantic segmentation model. It consists of two segments: (1) A novel MetaFormer-based encoder, termed the EffVisionFormer, is introduced. It captures multiscale image features efficiently. (2) A lightweight decoder which utilizes multiscale image features from the encoder is applied to conduct rapid yet accurate segmented result. The proposed EffSegmentNet achieves remarkable performance which takes the inference speed, accuracy, and model parameters into account. On the Cityscapes test set, we attain 71.9% mIoU with 195.1 frames per second (FPS) on a NVIDIA RTX 2080Ti card. Furthermore, the proposed EffSegmentNet utilizes only 4.4 million parameters, which demonstrates its advantage on real-time segmentation. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/638461 | ISBN: | 9798350300673 | DOI: | 10.1109/APSIPAASC58517.2023.10317131 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。