Large scale automatic image annotation based on convolutional neural network |
| |
| Affiliation: | 1. Indian Institute of Information Technology Chittoor, Sri City, India;2. Indian Institute of Information Technology Allahabad, India;1. College of Information and Control Engineering, China University of Petroleum (East China), Qingdao 266580, China;2. Advanced Analytics Institute, University of Technology Sydney, Sydney 2007, Australia;3. School of Information Science and Engineering, Yunnan University, Kunming 650091, China;4. Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China;5. Chinese University of Hong Kong, Shatin, Hong Kong;1. National Institute of Telecommunications and ICT, Oran, Algeria;2. PRISME Laboratory, University of Orléans, France;3. XLIM Laboratory, University of Poitiers, France;1. SP_Lab, Electronics Dept., Mentouri University of Constantine, Algeria;2. SP_Lab and Electrical Eng. Dept., Larbi Ben Mhidi University of Oum el Bouaghi, Algeria;1. School of Info. and Cont. Eng., China Univ. of Mining and Technology, China;2. School of Info. and Elec. Eng., Jiangsu Vocational College of Business, China;3. The State Info. Center of P.R. China, China;4. BJUT Faculty of Info. Tech., Beijing University of Technology, China |
| |
| Abstract: | Automatic image annotation is one of the most important challenges in computer vision, which is critical to many real-world researches and applications. In this paper, we focus on the issue of large scale image annotation with deep learning. Firstly, considering the existing image data, especially the network images, most of the labels of themselves are inaccurate or imprecise. We propose a Multitask Voting (MV) method, which can improve the accuracy of original annotation to a certain extent, thereby enhancing the training effect of the model. Secondly, the MV method can also achieve the adaptive label, whereas most existing methods pre-specify the number of tags to be selected. Additionally, based on convolutional neural network, a large scale image annotation model MVAIACNN is constructed. Finally, we evaluate the performance with experiments on the MIRFlickr25K and NUS-WIDE datasets, and compare with other methods, demonstrating the effectiveness of the MVAIACNN. |
| |
| Keywords: | Deep learning Automatic image annotation Adaptive label Multitasking Convolutional neural network |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
