Jianyang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jianyang Zhang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Changru Nie
Southwest Jiaotong University, Chengdu, Sichuan, China
1 shared publication Die Hong
The Department of Gynecologic Oncology, Women's Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang 310006, China
1 shared publication- Fengmao Lv
Southwest Jiaotong University, Chengdu, Sichuan, China
1 shared publication - Guosheng Lin
Nanyang technological university, Singapore, Singapore
1 shared publication - Guowu Yang
University of Electronic Science and Technology of China
1 shared publication - Jian Zou
Department of Biostatistics, University of Pittsburgh, Pittsburgh, PA, USA
1 shared publication
Latest Publications
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8345-8354
Rethinking the Effect of Uninformative Class Name in Prompt Learning
Large pre-trained vision-language models like CLIP have shown amazing zero-shot recognition performance. To adapt pre-trained vision-language models to downstream tasks, recent studies have focused on the learnable context + class name paradigm, which learns continuous prompt contexts on downstream datasets. In practice, the learned prompt context tends to overfit the base categories and cannot generalize well to novel categories out of the training data. Recent works have also noticed this problem and have proposed several improvements. In this work, we draw a new insight based on empirical analysis, that is, uninformative class names lead to degraded base-to-novel generalization performance in prompt learning, which is usually overlooked by existing works. Under this motivation, we advocate to improve the base-to-novel generalization performance of prompt learning by enhancing the semantic richness of class names. We coin our approach as the Information Disengagement based Associative Prompt Learning (IDAPL) mechanism which considers the associative, meanwhile, decoupled learning of prompt context and class name embedding. IDAPL can effectively alleviate the phenomenon of learnable context overfitting to base classes, meanwhile, learning more informative semantic representation of base classes by fine-tuning the class name embedding, leading to improved performance on both base and novel classes. Experimental results on eleven widely used few-shot learning benchmarks clearly validate the effectiveness of our proposed approach. Code is available at https://github.com/tiggers23/IDAPL
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8345-8354
Open AccessRethinking the Effect of Uninformative Class Name in Prompt Learning
Large pre-trained vision-language models like CLIP have shown amazing zero-shot recognition performance. To adapt pre-trained vision-language models to downstream tasks, recent studies have focused on the learnable context + class name paradigm, which learns continuous prompt contexts on downstream datasets. In practice, the learned prompt context tends to overfit the base categories and cannot generalize well to novel categories out of the training data. Recent works have also noticed this problem and have proposed several improvements. In this work, we draw a new insight based on empirical analysis, that is, uninformative class names lead to degraded base-to-novel generalization performance in prompt learning, which is usually overlooked by existing works. Under this motivation, we advocate to improve the base-to-novel generalization performance of prompt learning by enhancing the semantic richness of class names. We coin our approach as the Information Disengagement based Associative Prompt Learning (IDAPL) mechanism which considers the associative, meanwhile, decoupled learning of prompt context and class name embedding. IDAPL can effectively alleviate the phenomenon of learnable context overfitting to base classes, meanwhile, learning more informative semantic representation of base classes by fine-tuning the class name embedding, leading to improved performance on both base and novel classes. Experimental results on eleven widely used few-shot learning benchmarks clearly validate the effectiveness of our proposed approach. Code is available at https://github.com/tiggers23/IDAPL
- Open Access
- 20 May 2016
- Published by Impact Journals, LLC in Oncotarget
- Vol. 7 (26) , 40135-40147
Variants in human papillomavirus receptor and associated genes are associated with type-specific HPV infection and lesion progression of the cervix
Variants in human papillomavirus receptor and associated genes are associated with type-specific HPV infection and lesion progression of the cervix
- 20 May 2016
- Published by Impact Journals, LLC in Oncotarget
- Vol. 7 (26) , 40135-40147
Open AccessVariants in human papillomavirus receptor and associated genes are associated with type-specific HPV infection and lesion progression of the cervix
Variants in human papillomavirus receptor and associated genes are associated with type-specific HPV infection and lesion progression of the cervix