Search

Your search keyword '"Zhang, Hongjie"' showing total 4,476 results
Start Over Author "Zhang, Hongjie"
4,476 results on '"Zhang, Hongjie"'

55. Feature Extraction Framework based on Contrastive Learning with Adaptive Positive and Negative Samples

Author

Zhang, Hongjie

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Abstract

In this study, we propose a feature extraction framework based on contrastive learning with adaptive positive and negative samples (CL-FEFA) that is suitable for unsupervised, supervised, and semi-supervised single-view feature extraction. CL-FEFA constructs adaptively the positive and negative samples from the results of feature extraction, which makes it more appropriate and accurate. Thereafter, the discriminative features are re extracted to according to InfoNCE loss based on previous positive and negative samples, which will make the intra-class samples more compact and the inter-class samples more dispersed. At the same time, using the potential structure information of subspace samples to dynamically construct positive and negative samples can make our framework more robust to noisy data. Furthermore, CL-FEFA considers the mutual information between positive samples, that is, similar samples in potential structures, which provides theoretical support for its advantages in feature extraction. The final numerical experiments prove that the proposed framework has a strong advantage over the traditional feature extraction methods and contrastive learning methods.

Published
2022

64. INTERACTIVE KNOWLEDGE LEARNING BY ARTIFICIAL INTELLIGENCE FOR SMALLHOLDERS

Author

Weili ZHANG, Renlian ZHANG, Hongjie JI, Anja SEVERIN, Zhaojun LI

Subjects
artificial intelligence, extension system, non-point source pollution control, smallholders, fertilization, Agriculture (General), S1-972
Abstract

Enhancement of farming management relies heavily on enhancing farmer knowledge. In the past, both the direct learning approach and the personnel extension system for improving fertilization practices of smallholders has proven insufficiently effective. Therefore, this article proposes an interactive knowledge learning approach using artificial intelligence as a promising alternative. The system consists of two parts. The first is a dialog interface that accepts information from farmers about their current farming practices. The second part is an intelligent decision system, which categorizes the information provided by farmers in two categories. The first consists of on-farm constraints, such as fertilizer resources, split application times and seasons. The second comprises knowledge-based practices by farmers, such as nutrient in- and output balance, ratios of different nutrients and the ratios of each split nutrient amount to the total nutrient input. The interactive knowledge learning approach aims to identify and rectify incorrect practices in the knowledge-based category while considering the farmer’s available finance, labor, and fertilizer resources. Investigations show that the interactive knowledge learning approach can make a strong contribution to prevention of the overuse of nitrogen and phosphorus fertilizers, and mitigating agricultural non-point source pollution.

Published
2023
Full Text
View/download PDF

94. Unified Framework for Feature Extraction based on Contrastive Learning

Author

Zhang, Hongjie

Subjects
Computer Science - Machine Learning
Abstract

Feature extraction is an efficient approach for alleviating the issue of dimensionality in high-dimensional data. As a popular self-supervised learning method, contrastive learning has recently garnered considerable attention. In this study, we proposed a unified framework based on a new perspective of contrastive learning (CL) that is suitable for both unsupervised and supervised feature extraction. The proposed framework first constructed two CL graph for uniquely defining the positive and negative pairs. Subsequently, the projection matrix was determined by minimizing the contrastive loss function. In addition, the proposed framework considered both similar and dissimilar samples to unify unsupervised and supervised feature extraction. Moreover, we propose the three specific methods: unsupervised contrastive learning method, supervised contrastive learning method 1 ,and supervised contrastive learning method 2. Finally, the numerical experiments on five real datasets demonstrated the superior performance of the proposed framework in comparison to the existing methods.

Published
2021

96. Hybrid Models for Open Set Recognition

Author

Zhang, Hongjie, Li, Ang, Guo, Jie, and Guo, Yanwen

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Open set recognition requires a classifier to detect samples not belonging to any of the classes in its training set. Existing methods fit a probability distribution to the training samples on their embedding space and detect outliers according to this distribution. The embedding space is often obtained from a discriminative classifier. However, such discriminative representation focuses only on known classes, which may not be critical for distinguishing the unknown classes. We argue that the representation space should be jointly learned from the inlier classifier and the density estimator (served as an outlier detector). We propose the OpenHybrid framework, which is composed of an encoder to encode the input data into a joint embedding space, a classifier to classify samples to inlier classes, and a flow-based density estimator to detect whether a sample belongs to the unknown category. A typical problem of existing flow-based models is that they may assign a higher likelihood to outliers. However, we empirically observe that such an issue does not occur in our experiments when learning a joint representation for discriminative and generative components. Experiments on standard open set benchmarks also reveal that an end-to-end trained OpenHybrid model significantly outperforms state-of-the-art methods and flow-based baselines., Comment: 16 pages, 4 figures

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results