Fast scene labeling via structural inference

• Main Authors: ZHANG, Huaidong, HAN, Chu, ZHANG, Xiaodan, DU, Yong, XU, Xuemiao, HAN, Guoqiang, QIN, Jing, Shengfeng HE
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: LSTM; Structural inference; Scene labeling; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/7838; https://ink.library.smu.edu.sg/context/sis_research/article/8841/viewcontent/1_s2.0_S0925231221003428_main.pdf
• Institution: Singapore Management University

Scene labeling or parsing aims to assign pixelwise semantic labels for an input image. Existing CNN-based models cannot leverage the label dependencies, while RNN-based models predict labels within the local context. In this paper, we propose a fast LSTM scene labeling network via structural inferen...