Abstract:
Deep learning models often use a flat softmax layer to classify samples after feature extraction in visual classification tasks. However, it is hard to make a single deci...Show MoreMetadata
Abstract:
Deep learning models often use a flat softmax layer to classify samples after feature extraction in visual classification tasks. However, it is hard to make a single decision of finding the true label from massive classes. In this scenario, hierarchical classification is proved to be an effective solution and can be utilized to replace the softmax layer. A key issue of hierarchical classification is to construct a good label structure, which is very significant for classification performance. Several works have been proposed to address the issue, but they have some limitations and are almost designed heuristically. In this article, inspired by fuzzy rough set theory, we propose a deep fuzzy tree model which learns a better tree structure and classifiers for hierarchical classification with theory guarantee. Experimental results show the effectiveness and efficiency of the proposed model in various visual classification datasets.
Published in: IEEE Transactions on Fuzzy Systems ( Volume: 28, Issue: 7, July 2020)
Funding Agency:
School of Artificial Intelligence, Tianjin University, Tianjin, China
Yu Wang received the B.S. degree in communication engineering and the M.S. degree in software engineering from Tianjin University, Tianjin, China, in 2013 and 2016, respectively. He is currently working toward the Ph.D. degree in computer application techniques with the School of Intelligence and Computing, Tianjin University, China.
His research interests include hierarchical learning and image classification in data mini...Show More
Yu Wang received the B.S. degree in communication engineering and the M.S. degree in software engineering from Tianjin University, Tianjin, China, in 2013 and 2016, respectively. He is currently working toward the Ph.D. degree in computer application techniques with the School of Intelligence and Computing, Tianjin University, China.
His research interests include hierarchical learning and image classification in data mini...View more
School of Artificial Intelligence, Tianjin University, Tianjin, China
Qinghua Hu received the B.S., M.S., and Ph.D. degrees in energy science engineering from the Harbin Institute of Technology, Harbin, China, in 1999, 2002, and 2008, respectively.
He was a Postdoctoral Fellow with the Department of Computing, Hong Kong Polytechnic University, Kowloon, Hong Kong, from 2009 to 2011. He is currently the Dean of the School of Artificial Intelligence, the Vice Chairman of the Tianjin Branch of C...Show More
Qinghua Hu received the B.S., M.S., and Ph.D. degrees in energy science engineering from the Harbin Institute of Technology, Harbin, China, in 1999, 2002, and 2008, respectively.
He was a Postdoctoral Fellow with the Department of Computing, Hong Kong Polytechnic University, Kowloon, Hong Kong, from 2009 to 2011. He is currently the Dean of the School of Artificial Intelligence, the Vice Chairman of the Tianjin Branch of C...View more
School of Artificial Intelligence, Tianjin University, Tianjin, China
Pengfei Zhu received the B.S. degree in power engineering and the M.S. degree in power machinery and engineering from the Harbin Institute of Technology, Harbin, China, in 2009 and 2011, respectively, and the Ph.D. degree in computer vision from Hong Kong Polytechnic University, Hong Kong, China, in 2015.
Currently, he is an Associate Professor with the College of Intelligence and Computing, Tianjin University, Tianjin, Ch...Show More
Pengfei Zhu received the B.S. degree in power engineering and the M.S. degree in power machinery and engineering from the Harbin Institute of Technology, Harbin, China, in 2009 and 2011, respectively, and the Ph.D. degree in computer vision from Hong Kong Polytechnic University, Hong Kong, China, in 2015.
Currently, he is an Associate Professor with the College of Intelligence and Computing, Tianjin University, Tianjin, Ch...View more
School of Artificial Intelligent, Heibei University of Technology, Tianjin, China
Linhao Li received the B.S. degree in applied mathematics, the M.S. degree in computational mathematics, and the Ph.D. degree in computer science from Tianjin University, Tianjin, China, in 2012, 2014, and 2019, respectively.
He is currently working as an Assistant Professor with the School of Artificial Intelligent, Heibei University of Technology, Tianjin. His research interests include quantization and hashing learning,...Show More
Linhao Li received the B.S. degree in applied mathematics, the M.S. degree in computational mathematics, and the Ph.D. degree in computer science from Tianjin University, Tianjin, China, in 2012, 2014, and 2019, respectively.
He is currently working as an Assistant Professor with the School of Artificial Intelligent, Heibei University of Technology, Tianjin. His research interests include quantization and hashing learning,...View more
School of Artificial Intelligence, Tianjin University, Tianjin, China
Bingxu Lu received the B.S. degree in computer science and technology from the Nanjing Agriculture University, Nanjing, China, in 2016. Currently, he is working toward the Ph.D. degree in computer application techniques with the College of Intelligence and Computing, Tianjin University, China.
His research interests include deep learning and computer vision.
Bingxu Lu received the B.S. degree in computer science and technology from the Nanjing Agriculture University, Nanjing, China, in 2016. Currently, he is working toward the Ph.D. degree in computer application techniques with the College of Intelligence and Computing, Tianjin University, China.
His research interests include deep learning and computer vision.View more
School of Computer Science, University of Nottingham, Nottingham, U.K.
Jonathan M. Garibaldi received the B.Sc. (Hons.) degree in physics from Bristol University, Bristol, U.K., in 1984, and the M.Sc. degree in intelligent systems and the Ph.D. degree in uncertainty handling in immediate neonatal assessment from the University of Plymouth, Plymouth, U.K., in 1990 and 1997, respectively.
He is Head of the School of Computer Science, University of Nottingham, Nottingham, U.K., and leads the Int...Show More
Jonathan M. Garibaldi received the B.Sc. (Hons.) degree in physics from Bristol University, Bristol, U.K., in 1984, and the M.Sc. degree in intelligent systems and the Ph.D. degree in uncertainty handling in immediate neonatal assessment from the University of Plymouth, Plymouth, U.K., in 1990 and 1997, respectively.
He is Head of the School of Computer Science, University of Nottingham, Nottingham, U.K., and leads the Int...View more
Science and Technology on Thermal Energy and Power Laboratory, Wuhan, China
Xianling Li received the B.S., M.S., and Ph.D. degrees in power mechanical engineering from the Harbin Institute of Technology, Harbin, China, in 2005, 2007, and 2011, respectively.
He is a Senior Engineer with the Science and Technology on Thermal Energy and Power Laboratory, Wuhan, China. His interests include big data, fault diagnosis of complex power system, and intelligent control.
Xianling Li received the B.S., M.S., and Ph.D. degrees in power mechanical engineering from the Harbin Institute of Technology, Harbin, China, in 2005, 2007, and 2011, respectively.
He is a Senior Engineer with the Science and Technology on Thermal Energy and Power Laboratory, Wuhan, China. His interests include big data, fault diagnosis of complex power system, and intelligent control.View more
Contents School of Artificial Intelligence, Tianjin University, Tianjin, China
Yu Wang received the B.S. degree in communication engineering and the M.S. degree in software engineering from Tianjin University, Tianjin, China, in 2013 and 2016, respectively. He is currently working toward the Ph.D. degree in computer application techniques with the School of Intelligence and Computing, Tianjin University, China.
His research interests include hierarchical learning and image classification in data mining and machine learning.
Yu Wang received the B.S. degree in communication engineering and the M.S. degree in software engineering from Tianjin University, Tianjin, China, in 2013 and 2016, respectively. He is currently working toward the Ph.D. degree in computer application techniques with the School of Intelligence and Computing, Tianjin University, China.
His research interests include hierarchical learning and image classification in data mining and machine learning.View more
School of Artificial Intelligence, Tianjin University, Tianjin, China
Qinghua Hu received the B.S., M.S., and Ph.D. degrees in energy science engineering from the Harbin Institute of Technology, Harbin, China, in 1999, 2002, and 2008, respectively.
He was a Postdoctoral Fellow with the Department of Computing, Hong Kong Polytechnic University, Kowloon, Hong Kong, from 2009 to 2011. He is currently the Dean of the School of Artificial Intelligence, the Vice Chairman of the Tianjin Branch of China Computer Federation, and the Vice Director of the SIG Granular Computing and Knowledge Discovery, and the Chinese Association of Artificial Intelligence. He has published over 200 peer-reviewed articles. His current research interests include uncertainty modeling in big data, machine learning with multi-modality data, and intelligent unmanned systems.
Dr. Hu is an Associate Editor of the IEEE Transactions on Fuzzy Systems, Acta Automatica Sinica, and Energies.
Qinghua Hu received the B.S., M.S., and Ph.D. degrees in energy science engineering from the Harbin Institute of Technology, Harbin, China, in 1999, 2002, and 2008, respectively.
He was a Postdoctoral Fellow with the Department of Computing, Hong Kong Polytechnic University, Kowloon, Hong Kong, from 2009 to 2011. He is currently the Dean of the School of Artificial Intelligence, the Vice Chairman of the Tianjin Branch of China Computer Federation, and the Vice Director of the SIG Granular Computing and Knowledge Discovery, and the Chinese Association of Artificial Intelligence. He has published over 200 peer-reviewed articles. His current research interests include uncertainty modeling in big data, machine learning with multi-modality data, and intelligent unmanned systems.
Dr. Hu is an Associate Editor of the IEEE Transactions on Fuzzy Systems, Acta Automatica Sinica, and Energies.View more
School of Artificial Intelligence, Tianjin University, Tianjin, China
Pengfei Zhu received the B.S. degree in power engineering and the M.S. degree in power machinery and engineering from the Harbin Institute of Technology, Harbin, China, in 2009 and 2011, respectively, and the Ph.D. degree in computer vision from Hong Kong Polytechnic University, Hong Kong, China, in 2015.
Currently, he is an Associate Professor with the College of Intelligence and Computing, Tianjin University, Tianjin, China. He has authored/co-authored more than 30 articles in conferences and journals. His research interests include machine learning and computer vision.
Dr. Zhu is the local arrangement Chair of International Joint Conference On Rough Sets (IJCRS) 2015, China Conference on Machine Learning (CCML) 2017, and Chinese Conference on Computer Vision (CCCV) 2017.
Pengfei Zhu received the B.S. degree in power engineering and the M.S. degree in power machinery and engineering from the Harbin Institute of Technology, Harbin, China, in 2009 and 2011, respectively, and the Ph.D. degree in computer vision from Hong Kong Polytechnic University, Hong Kong, China, in 2015.
Currently, he is an Associate Professor with the College of Intelligence and Computing, Tianjin University, Tianjin, China. He has authored/co-authored more than 30 articles in conferences and journals. His research interests include machine learning and computer vision.
Dr. Zhu is the local arrangement Chair of International Joint Conference On Rough Sets (IJCRS) 2015, China Conference on Machine Learning (CCML) 2017, and Chinese Conference on Computer Vision (CCCV) 2017.View more
School of Artificial Intelligent, Heibei University of Technology, Tianjin, China
Linhao Li received the B.S. degree in applied mathematics, the M.S. degree in computational mathematics, and the Ph.D. degree in computer science from Tianjin University, Tianjin, China, in 2012, 2014, and 2019, respectively.
He is currently working as an Assistant Professor with the School of Artificial Intelligent, Heibei University of Technology, Tianjin. His research interests include quantization and hashing learning, sparse signal recovery, background modeling, and foreground detection.
Linhao Li received the B.S. degree in applied mathematics, the M.S. degree in computational mathematics, and the Ph.D. degree in computer science from Tianjin University, Tianjin, China, in 2012, 2014, and 2019, respectively.
He is currently working as an Assistant Professor with the School of Artificial Intelligent, Heibei University of Technology, Tianjin. His research interests include quantization and hashing learning, sparse signal recovery, background modeling, and foreground detection.View more
School of Artificial Intelligence, Tianjin University, Tianjin, China
Bingxu Lu received the B.S. degree in computer science and technology from the Nanjing Agriculture University, Nanjing, China, in 2016. Currently, he is working toward the Ph.D. degree in computer application techniques with the College of Intelligence and Computing, Tianjin University, China.
His research interests include deep learning and computer vision.
Bingxu Lu received the B.S. degree in computer science and technology from the Nanjing Agriculture University, Nanjing, China, in 2016. Currently, he is working toward the Ph.D. degree in computer application techniques with the College of Intelligence and Computing, Tianjin University, China.
His research interests include deep learning and computer vision.View more
School of Computer Science, University of Nottingham, Nottingham, U.K.
Jonathan M. Garibaldi received the B.Sc. (Hons.) degree in physics from Bristol University, Bristol, U.K., in 1984, and the M.Sc. degree in intelligent systems and the Ph.D. degree in uncertainty handling in immediate neonatal assessment from the University of Plymouth, Plymouth, U.K., in 1990 and 1997, respectively.
He is Head of the School of Computer Science, University of Nottingham, Nottingham, U.K., and leads the Intelligent Modelling and Analysis (IMA) research group. The IMA research group undertakes research into intelligent modeling, utilizing data analysis and transformation techniques to enable deeper and clearer understanding of complex problems. He has made many theoretical and practical contributions in fuzzy sets and systems, and in a wide range of generic machine learning techniques in real-world applications. He has published over 200 articles on fuzzy systems and intelligent data analysis. His main research interests include modeling uncertainty and variation in human reasoning, and in modeling and interpreting complex data to enable better decision-making, particularly in medical domains.
Dr. Garibaldi is the Editor-in-Chief of the IEEE Transactions on Fuzzy Systems (2017). He has served regularly in the organizing committees and program committees of a range of leading international conferences and workshops, such as FUZZ-IEEE.
Jonathan M. Garibaldi received the B.Sc. (Hons.) degree in physics from Bristol University, Bristol, U.K., in 1984, and the M.Sc. degree in intelligent systems and the Ph.D. degree in uncertainty handling in immediate neonatal assessment from the University of Plymouth, Plymouth, U.K., in 1990 and 1997, respectively.
He is Head of the School of Computer Science, University of Nottingham, Nottingham, U.K., and leads the Intelligent Modelling and Analysis (IMA) research group. The IMA research group undertakes research into intelligent modeling, utilizing data analysis and transformation techniques to enable deeper and clearer understanding of complex problems. He has made many theoretical and practical contributions in fuzzy sets and systems, and in a wide range of generic machine learning techniques in real-world applications. He has published over 200 articles on fuzzy systems and intelligent data analysis. His main research interests include modeling uncertainty and variation in human reasoning, and in modeling and interpreting complex data to enable better decision-making, particularly in medical domains.
Dr. Garibaldi is the Editor-in-Chief of the IEEE Transactions on Fuzzy Systems (2017). He has served regularly in the organizing committees and program committees of a range of leading international conferences and workshops, such as FUZZ-IEEE.View more
Science and Technology on Thermal Energy and Power Laboratory, Wuhan, China
Xianling Li received the B.S., M.S., and Ph.D. degrees in power mechanical engineering from the Harbin Institute of Technology, Harbin, China, in 2005, 2007, and 2011, respectively.
He is a Senior Engineer with the Science and Technology on Thermal Energy and Power Laboratory, Wuhan, China. His interests include big data, fault diagnosis of complex power system, and intelligent control.
Xianling Li received the B.S., M.S., and Ph.D. degrees in power mechanical engineering from the Harbin Institute of Technology, Harbin, China, in 2005, 2007, and 2011, respectively.
He is a Senior Engineer with the Science and Technology on Thermal Energy and Power Laboratory, Wuhan, China. His interests include big data, fault diagnosis of complex power system, and intelligent control.View more
