文献类型：期刊文献

英文题名：Semantic Supplementary Network With Prior Information for Multi-Label Image Classification

作者：Wang, Zhe[1,2];Fang, Zhongli[1,2];Li, Dongdong[2];Yang, Hai[2];Du, Wenli[1]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Smart Mfg Energy Chem Proc, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China

年份：2022

卷号：32

期号：4

起止页码：1848

外文期刊名：IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY

收录：;EI(收录号：20212310459871);WOS:【SCI-EXPANDED(收录号:WOS:000778973700014)】；

基金：This work was supported in part by the Shanghai Science and Technology Program "Distributed and generative few-shot algorithm and theory research" under Grant 20511100600 and in part by the Natural Science Foundation of China under Grant 62076094. This article was recommended by Associate Editor Y. Zhang.

语种：英文

外文关键词：Semantics; Feature extraction; Predictive models; Image recognition; Task analysis; Sports; Deep learning; Multi-label classification; semantic supplementary network; prior information; deep neural network

摘要：The multi-label image classification problem is one of the most important problems in the field of computer vision, which needs to predict and output all the labels in an image. Multiple labels to be classified in an image increases the difficulty of image classification, and multi-label image classification usually requires additional attention to the positions of the object with different scales and poses. Hence, how to use the dependency relationship between labels to improve the recognition accuracy is an important problem when the object is difficult to directly identify. In this paper, we propose a designed network called the Semantic Supplementary Network with Prior Information (SSNP) to address this problem. The proposed SSNP first generates prior information by using a prior information network with different convolutional layers. Then the semantic supplementary module generates semantic information of the potential labels that is highly relevant to the current information based on the prior information, thereby effectively using the dependency relationship between the labels to improve the classification accuracy. Different from existing methods which pay more attention to the image feature extraction process, we focus on the impact of high-level semantic information generated after feature extraction on the results and tap the potential of high-level semantic information through a semantic supplementary module to strengthen the potential dependence between labels. Experimental results on public benchmark datasets demonstrate that the proposed architecture achieves the state-of-the-art performance, especially when predicting some semantically dependent labels.