Exploring images with deep learning for classification, retrieval and synthesis

Liu, Y. (2018)

Doctoral Thesis

In 2018, the number of mobile phone users will reach about 4.9 billion. Assuming an average of 5 photos taken per day using the built-in cameras would result in about 9 trillion photos annually. Thus, it becomes challenging to mine semantic information from such a huge amount of visual data. To solve this challenge, deep learning, an important sub-field in machine learning, has achieved impressive developments in recent years. Inspired by its success, this thesis aims to develop new approaches in deep learning to explore and analyze image data from three research themes: classification, retrieval and synthesis. In summary, the research of this thesis contributes at three levels: models and algorithms, practical scenarios and empirical analysis. First, this work presents new approaches based on deep learning to address eight research questions regarding the three themes. In addition, it aims towards adapting the approaches to practical scenarios in real world. Furthermore, this thesis provides numerous experiments and in-depth analysis, which can help motivate further research on the three research themes.

Computer Vision
Multimedia Applications
Deep Learning

• Multimedia Applications
• Deep Learning

• All authors: Liu, Y.
• Supervisor: Kok, J.N.; Lew, M.S.
• Committee: Plaat, A.; Bäck, T.H.W.; Kraaij, W.; Trautmann, H.; Hanjalic, A.; Lelieveldt, B.P.F.; Poppe, R.
• Qualification: Doctor (dr.)
• Awarding Institution: Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University
• Date: 2018-10-24
• Title of host publication: ASCI dissertation series
• ISBN (print): 9789463751391
• Name: 387
• Sponsorship: China Scholarship Council (CSC)