Ruixue Lian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ruixue Lian has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- William A. Sethares
University of Wisconsin-Madison
3 shared publications - Junjie Hu
School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China
2 shared publications - Andrew Messier
Arista Networks, Santa Clara, CA 95054, USA
1 shared publication - Elisa Ou
Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA
1 shared publication - Paul Messier
Lens Media Lab, Yale University, New Haven, CT, United States of America
1 shared publication
Latest Publications
- Open Access
Learning Label Hierarchy with Supervised Contrastive Learning
Supervised contrastive learning (SCL) frameworks treat each class as independent and thus consider all classes to be equally important. This neglects the common scenario in which label hierarchy exists, where fine-grained classes under the same category show more similarity than very different ones. This paper introduces a family of Label-Aware SCL methods (LASCL) that incorporates hierarchical information to SCL by leveraging similarities between classes, resulting in creating a more well-structured and discriminative feature space. This is achieved by first adjusting the distance between instances based on measures of the proximity of their classes with the scaled instance-instance-wise contrastive. An additional instance-center-wise contrastive is introduced to move within-class examples closer to their centers, which are represented by a set of learnable label parameters. The learned label parameters can be directly used as a nearest neighbor classifier without further finetuning. In this way, a better feature representation is generated with improvements of intra-cluster compactness and inter-cluster separation. Experiments on three datasets show that the proposed LASCL works well on text classification of distinguishing a single label among multi-labels, outperforming the baseline supervised approaches. Our code is publicly available.
Open AccessLearning Label Hierarchy with Supervised Contrastive Learning
Supervised contrastive learning (SCL) frameworks treat each class as independent and thus consider all classes to be equally important. This neglects the common scenario in which label hierarchy exists, where fine-grained classes under the same category show more similarity than very different ones. This paper introduces a family of Label-Aware SCL methods (LASCL) that incorporates hierarchical information to SCL by leveraging similarities between classes, resulting in creating a more well-structured and discriminative feature space. This is achieved by first adjusting the distance between instances based on measures of the proximity of their classes with the scaled instance-instance-wise contrastive. An additional instance-center-wise contrastive is introduced to move within-class examples closer to their centers, which are represented by a set of learnable label parameters. The learned label parameters can be directly used as a nearest neighbor classifier without further finetuning. In this way, a better feature representation is generated with improvements of intra-cluster compactness and inter-cluster separation. Experiments on three datasets show that the proposed LASCL works well on text classification of distinguishing a single label among multi-labels, outperforming the baseline supervised approaches. Our code is publicly available.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1569-1581
Learning Label Hierarchy with Supervised Contrastive Learning
Ruixue Lian, William Sethares, Junjie Hu. Findings of the Association for Computational Linguistics: EACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1569-1581
Open AccessLearning Label Hierarchy with Supervised Contrastive Learning
Ruixue Lian, William Sethares, Junjie Hu. Findings of the Association for Computational Linguistics: EACL 2024. 2024.
- Open Access
The Watermark Imaging System: Revealing the Internal Structure of Historical Papers
This paper introduces the Watermark Imaging System (WImSy) which can be used to photograph, document, and study sheets of paper. The WImSy provides surface images, raking light images, and transmitted light images of the paper, all in perfect alignment. We develop algorithms that exploit this alignment by combining several images together in a process that mimics both the “surface image removal” technique and the method of “high dynamic range” photographs. An improved optimization criterion and an automatic parameter selection procedure streamline the process and make it practical for art historians and conservators to extract the relevant information to study watermarks. The effectiveness of the method is demonstrated in several experiments on images taken with the WImSy at the Metropolitan Museum of Art in New York and at the Getty Museum in Los Angeles, and the results are compared with manually optimized images.
Open AccessThe Watermark Imaging System: Revealing the Internal Structure of Historical Papers
This paper introduces the Watermark Imaging System (WImSy) which can be used to photograph, document, and study sheets of paper. The WImSy provides surface images, raking light images, and transmitted light images of the paper, all in perfect alignment. We develop algorithms that exploit this alignment by combining several images together in a process that mimics both the “surface image removal” technique and the method of “high dynamic range” photographs. An improved optimization criterion and an automatic parameter selection procedure streamline the process and make it practical for art historians and conservators to extract the relevant information to study watermarks. The effectiveness of the method is demonstrated in several experiments on images taken with the WImSy at the Metropolitan Museum of Art in New York and at the Getty Museum in Los Angeles, and the results are compared with manually optimized images.