Hao Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hao Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Peng Hu
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
3 shared publicationsRuxin Zhao
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
3 shared publicationsYanchao Li
School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China
3 shared publications- Yongli Wang
Nanjing University of Science and Technology
3 shared publications Gang Xiao
Science and Technology on Complex Systems Simulation Laboratory, Beijing, China
2 shared publications- Bowen Sun
School of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai 201209, China
1 shared publication
Latest Publications
- 21 March 2025
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 34 (09)
Exploring Uncertainty and Representativeness for Deep Active Learning
Albeit the considerable advances that are achieved by convolutional neural networks (CNN) in active learning, simultaneously investing multiple criteria such as uncertainty and representativeness when sampling informative images still remains a challenging issue. In this work, we develop and evaluate an active learning method called Exploring Uncertainty and Representativeness in Deep Active Learning (EURDAL), to iteratively boost the generalization capacity of the CNN backbone for image classification. To be specific, we introduce two adversarial image classifiers appended to the CNN backbone, and the uncertainty is expounded by the prediction discrepancy of the two adversarial classifiers. Besides, the ([ ])-tuplet loss, which was developed in deep metric learning, is imposed on the CNN backbone, to force CNN to extract discriminative features of unlabeled images. After that, the representativeness is defined by the distance proportion between the given example to its own centroid and the given example to all cluster centroids. With the integration of the learned uncertainty and representativeness, the most informative images will be selected while the noisy ones will be suppressed at each iteration of active supervision. Intensive image classification experiments are conducted on three benchmark datasets, and the encouraging results demonstrate the superiority and effectiveness of our proposed EURDAL network compared with some current competitive active learning methods.
- 21 March 2025
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 34 (09)
Exploring Uncertainty and Representativeness for Deep Active Learning
Albeit the considerable advances that are achieved by convolutional neural networks (CNN) in active learning, simultaneously investing multiple criteria such as uncertainty and representativeness when sampling informative images still remains a challenging issue. In this work, we develop and evaluate an active learning method called Exploring Uncertainty and Representativeness in Deep Active Learning (EURDAL), to iteratively boost the generalization capacity of the CNN backbone for image classification. To be specific, we introduce two adversarial image classifiers appended to the CNN backbone, and the uncertainty is expounded by the prediction discrepancy of the two adversarial classifiers. Besides, the ([ ])-tuplet loss, which was developed in deep metric learning, is imposed on the CNN backbone, to force CNN to extract discriminative features of unlabeled images. After that, the representativeness is defined by the distance proportion between the given example to its own centroid and the given example to all cluster centroids. With the integration of the learned uncertainty and representativeness, the most informative images will be selected while the noisy ones will be suppressed at each iteration of active supervision. Intensive image classification experiments are conducted on three benchmark datasets, and the encouraging results demonstrate the superiority and effectiveness of our proposed EURDAL network compared with some current competitive active learning methods.
- 6 June 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (4) , 4162-4179
Small-target ship detection in SAR images based on densely connected deep neural network with attention in complex scenes
- 6 June 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (4) , 4162-4179
Small-target ship detection in SAR images based on densely connected deep neural network with attention in complex scenes
- 29 December 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 51 (6) , 3490
Correction to: Batch mode active learning via adaptive criteria weights
- 29 December 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 51 (6) , 3490
Correction to: Batch mode active learning via adaptive criteria weights
- 14 November 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 51 (6) , 3475-3489
Batch mode active learning via adaptive criteria weights
- 14 November 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 51 (6) , 3475-3489
Batch mode active learning via adaptive criteria weights
- 20 July 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 50 (12) , 4394-4411
Joint local structure preservation and redundancy minimization for unsupervised feature selection
- 20 July 2020
- Published by Springer Nature in Applied Intelligence
- Vol. 50 (12) , 4394-4411
Joint local structure preservation and redundancy minimization for unsupervised feature selection