Qinghua Zhao

Dr. Qinghua Zhao

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 July 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
QZQinghua Zhao
Qinghua Zhao
XCXu Chen
Xu Chen
HZHui Zhang
Hui Zhang
XLXinlu Li
Xinlu Li

2 August 2023 in Electronics
Verified
Journal Article
Open access
PDF file
SYShan Yang
Shan Yang
YZYongfei Zhang
Yongfei Zhang
QZQinghua Zhao
Qinghua Zhao
YPYanglin Pu
Yanglin Pu
HYHangyuan Yang
Hangyuan Yang
Deep metric learning aims to learn a mapping function that projects input data into a high-dimensional embedding space, facilitating the clustering of similar data points while ensuring dissimilar ones are far apart. The most recent studies focus on designing a batch sampler and mining online triplets to achieve this purpose. Conventionally, hard negative mining schemes serve as the preferred batch sampler. However, most hard negative mining schemes search for hard examples in randomly selected mini-batches at each epoch, which often results in less-optimal hard examples and thus sub-optimal performances. Furthermore, Triplet Loss is commonly adopted to perform online triplet mining by pulling the hard positives close to and pushing the negatives away from the anchor. However, when the anchor in a triplet is an outlier, the positive example will be pulled away from the centroid of the cluster, thus resulting in a loose cluster and inferior performance. To address the above challenges, we propose the Prototype-based Support Example Miner (pSEM) and Triplet Loss (pTriplet Loss). First, we present a support example miner designed to mine the support classes on the prototype-based nearest neighbor graph of classes. Following this, we locate the support examples by searching for instances at the intersection between clusters of these support classes. Second, we develop a variant of Triplet Loss, referred to as a Prototype-based Triplet Loss. In our approach, a dynamically updated prototype is used to rectify outlier anchors, thus reducing their detrimental effects and facilitating a more robust formulation for Triplet Loss. Extensive experiments on typical Computer Vision (CV) and Natural Language Processing (NLP) tasks, namely person re-identification and few-shot relation extraction, demonstrated the effectiveness and generalizability of the proposed scheme, which consistently outperforms the state-of-the-art models.

28 November 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
QZQinghua Zhao
Qinghua Zhao
JLJiaang Li
Jiaang Li
JLJunfeng Liu
Junfeng Liu
ZKZhongfeng Kang
Zhongfeng Kang
ZZZenghui Zhou
Zenghui Zhou


1 January 2022
Verified
Conference Paper
Open access
PDF file
QZQinghua Zhao
Qinghua Zhao
SMShuai Ma
Shuai Ma
SRShuo Ren
Shuo Ren
Qinghua Zhao, Shuai Ma, Shuo Ren. Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2022.

31 March 2025 in Software Quality Journal
Verified
Journal Article
Closed access
PDF file
ZZZenghui Zhou
Zenghui Zhou
PPPak-Lok Poon
Pak-Lok Poon
TCTsong Yueh Chen
Tsong Yueh Chen
KQKun Qiu
Kun Qiu
QZQinghua Zhao
Qinghua Zhao
ZZZheng Zheng
Zheng Zheng