Search

Your search keyword '"Wang, Dahan"' showing total 102 results
Start Over Author "Wang, Dahan"
102 results on '"Wang, Dahan"'

1. CAMEL2: Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio

Author

Xu, Gang, Wang, Shuhao, Zhao, Lingyu, Chen, Xiao, Wang, Tongwei, Wang, Lang, Luo, Zhenwei, Wang, Dahan, Zhang, Zewen, Liu, Aijun, Ba, Wei, Song, Zhigang, Shi, Huaiyin, Zhong, Dingrong, and Ma, Jianpeng

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

Histopathology image analysis plays a crucial role in cancer diagnosis. However, training a clinically applicable segmentation algorithm requires pathologists to engage in labour-intensive labelling. In contrast, weakly supervised learning methods, which only require coarse-grained labels at the image level, can significantly reduce the labeling efforts. Unfortunately, while these methods perform reasonably well in slide-level prediction, their ability to locate cancerous regions, which is essential for many clinical applications, remains unsatisfactory. Previously, we proposed CAMEL, which achieves comparable results to those of fully supervised baselines in pixel-level segmentation. However, CAMEL requires 1,280x1,280 image-level binary annotations for positive WSIs. Here, we present CAMEL2, by introducing a threshold of the cancerous ratio for positive bags, it allows us to better utilize the information, consequently enabling us to scale up the image-level setting from 1,280x1,280 to 5,120x5,120 while maintaining the accuracy. Our results with various datasets, demonstrate that CAMEL2, with the help of 5,120x5,120 image-level binary annotations, which are easy to annotate, achieves comparable performance to that of a fully supervised baseline in both instance- and slide-level classifications., Comment: 41 pages, 13 figures, published in Advanced Intelligent Systems

Published
2023
Full Text
View/download PDF

7. CAMEL2: Enhancing Weakly Supervised Learning for Histopathology Images by Incorporating the Significance Ratio

Author

Xu, Gang, primary, Wang, Shuhao, additional, Zhao, Lingyu, additional, Chen, Xiao, additional, Wang, Tongwei, additional, Wang, Lang, additional, Luo, Zhenwei, additional, Wang, Dahan, additional, Zhang, Zewen, additional, Liu, Aijun, additional, Ba, Wei, additional, Song, Zhigang, additional, Shi, Huaiyin, additional, Zhong, Dingrong, additional, and Ma, Jianpeng, additional

Published
2024
Full Text
View/download PDF

15. Synthesis of biheteroaryls via2-methyl quinoline C(sp3)-H functionalization under metal-free conditions

Author

Wang, Dahan, Yang, Yuhan, Xiao, Fuhong, Liu, Jinbing, Mao, Guojiang, and Deng, Guo-Jun

Abstract

An acetic acid-promoted C(sp3)-H functionalization of 2-methyl quinoline, enaminoesters and elemental sulfur for the synthesis of 3,4,5-trisubstituted isothiazoles under metal-free conditions has been developed. This approach provides viable access to various 5-(quinolin-2-yl)isothiazoles in moderate to good yields with good functional group tolerance. Moreover, the success of the gram-scale reaction gives this reaction a great potential application.

Published
2024
Full Text
View/download PDF

28. Label Specific Features-Based Classifier Chains for Multi-Label Classification

Author

Wei Weng, Shunxiang Wu, Juan Wen, Chin-Ling Chen, and Wang Dahan

Subjects
Multi-label classification, General Computer Science, business.industry, Computer science, Feature vector, Classifier chains, General Engineering, Binary number, Pattern recognition, Space (commercial competition), ComputingMethodologies_PATTERNRECOGNITION, Feature (machine learning), General Materials Science, Noise (video), Artificial intelligence, label specific features, multi-label learning, lcsh:Electrical engineering. Electronics. Nuclear engineering, business, Classifier (UML), lcsh:TK1-9971
Abstract

Multi-label classification tackles the problems in which each instance is associated with multiple labels. Due to the interdependence among labels, exploiting label correlations is the main means to enhance the performances of classifiers and a variety of corresponding multi-label algorithms have been proposed. Among those algorithms Classifier Chains (CC) is one of the most effective methods. It induces binary classifiers for each label, and these classifiers are linked in a chain. In the chain, the labels predicted by previous classifiers are used as additional features for the current classifier. The original CC has two shortcomings which potentially decrease classification performances: random label ordering, noise in original and additional features. To deal with these problems, we propose a novel and effective algorithm named LSF-CC, i.e. Label Specific Features based Classifier Chain for multi-label classification. At first, a feature estimating technique is employed to produce a list of most relevant features and labels for each label. According to these lists, we define a chain to guarantee that the most frequent labels that appear in these lists are top-ranked. Then, label specific features can be selected from the original feature space and label space. Based on these label specific features, corresponding binary classifiers are learned for each label. Experiments on several multi-label data sets from various domains have shown that the proposed method outperforms well-established approaches.

Published
2020

30. Multi-Task Learning with Deep Dual-Path Network for Facial Attribute Recognition

Author

Shunzhi Zhu, Si Chen, Lai Xinyu, and Wang Dahan

Subjects
Scheme (programming language), business.industry, Computer science, Deep learning, Multi-task learning, Pattern recognition, Path network, DUAL (cognitive architecture), Class imbalance, Artificial intelligence, business, Scale (map), computer, computer.programming_language
Abstract

Facial attribute recognition is a popular and challenging research topic in computer vision. In the traditional deep learning based attribute recognition methods, the mid-level network features and the differences between attribute groups are not fully explored. To solve the above problem, a deep dual-path network is proposed for facial attribute recognition. In the multi-task learning framework, two sub-networks are employed to respectively extract the features of two attribute groups, i.e., local attributes and global ones, and designed with both different scale images and different depth networks. Furthermore, an adaptive Focal loss penalty scheme is developed to automatically assign weights to handle the class imbalance problem for facial attribute recognition. Experimental results on the challenging CelebA dataset show that the proposed method achieves the better performance than state-of-the-art methods.

Published
2020

31. Object Tracking with Multi-Classifier Fusion Based on Compressive Sensing and Multiple Instance Learning

Author

Xiaosen Chen, Chen Min, Wang Dahan, Jianghu Chen, Shunzhi Zhu, Si Chen, and Xiaoshun Lu

Subjects
0209 industrial biotechnology, Similarity (geometry), Article Subject, business.industry, Computer science, General Mathematics, Feature vector, Random projection, General Engineering, 02 engineering and technology, Object (computer science), Engineering (General). Civil engineering (General), 020901 industrial engineering & automation, Compressed sensing, Discriminative model, Video tracking, 0202 electrical engineering, electronic engineering, information engineering, QA1-939, Clutter, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, TA1-2040, business, Mathematics
Abstract

Object tracking is a critical research in computer vision and has attracted significant attention over the past few years. However, the traditional object tracking algorithms often suffer from the object drifting problem due to various challenging factors in complex environments such as object occlusion and background clutter. This paper proposes a robust and effective object tracking algorithm, called MCM, which combines compressive sensing and online multiple instance learning in a multi-classifier fusion framework. In this framework, we integrate the different discriminative classifiers by learning the varied and compressed feature vectors based on different random projection matrices. And then an improved online multiple instance learning mechanism SMILE is adopted, which introduces the relative similarity to select and weight the instances in the positive bag. The experiments show that the proposed algorithm can improve the performance of object tracking on the challenging video sequences.

Published
2020

40. Three‐Component Synthesis of 2‐Heteroaryl‐3‐hydroxybenzo[b]‐thiophenes under Transition‐Metal‐Free Conditions.

Author

Wang, Dahan, Xiao, Fuhong, Zhang, Feng, and Deng, Guo‐Jun

Subjects
*SULFUR, *RING formation (Chemistry)
Abstract

Main observation and conclusion: A convenient synthetic route to 2‐heteroaryl‐3‐hydroxybenzo[b]thiophene derivatives via K2CO3‐promoted multicomponent cyclization between o‐halogenated benzaldehyde, 2‐methylquinolines and sulfur powder has been demonstrated. This reaction is performed smoothly under simple conditions to give the corresponding products in moderate to good yields. The resultant 3‐hydroxybenzo[b]thiophenes have been proved to be versatile building blocks in a range of transition‐metal‐catalyzed cross‐coupling reactions. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

45. Copper‐Catalyzed Aerobic Oxidative Ring Expansion of Isatins: A Facile Entry to Isoquinolino‐Fused Quinazolinones.

Author

Wang, Dahan, Xiao, Fuhong, Zhang, Feng, Huang, Huawen, and Deng, Guo‐Jun

Subjects
*QUINAZOLINONES, *TETRAHYDROISOQUINOLINES, *FUNCTIONAL groups
Abstract

A copper‐catalyzed aerobic oxidative ring expansion reaction of isatins with 1,2,3,4‐tetrahydroisoquinoline for the synthesis of tetracyclic quinazolinones has been developed. This reaction is performed smoothly under simple conditions to give the corresponding products in moderate to good yields with good functional group tolerance. The capacity of the resultant 5H‐isoquinolino[1,2‐b]quinazolin‐8(6H)‐one for a range of palladium‐catalyzed directing C—H activation has been further demonstrated, thus giving a broader access to diverse tetracyclic quinazolinones. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

49. Efficient C−S Bond Formation by Direct Functionalization of C(sp3)−H Bond Adjacent to Heteroatoms under Metal‐Free Conditions.

Author

Zhao, Feng, Tan, Qi, Wang, Dahan, Chen, Jinjin, and Deng, Guo‐Jun

Subjects
SULFINATES, SULFIDES, SODIUM compounds, IODINE
Abstract

A simple and efficient method for the formation of C−S bond via direct functionalization of C(sp3)−H bond adjacent to heteroatoms was described under metal‐free conditions. In this work, stable and easily accessible sodium sulfinates were used as the thiolating agents to afford various aryl thioethers in moderate to excellent yields. Mechanistic explorations show that a radical pathyway is possibly involved during the transformations. [ABSTRACT FROM AUTHOR]

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results