Si-Yang Jiang

Welcome to Si-Yang's website

Siyang Jiang (蒋思阳)

I am a fresh Ph.D in Department of Information Engineering, The Chinese University of Hong Kong (CUHK) , supervised by Prof. Guoliang Xing. Before that, I worked with Prof. Ming-Syan Chen in NTU.

My research interest includes AIoT, Fedearated Learning, Few-shot Learning and high-performance computing

News

2022-08-07 Congratulations! One paper is accepted in JSCS. This work is the first work which I attended as a supervisor (with Prof. Hui Jiang). The first author is an undergraduate (grade three) student when we submitted this work.
2022-05-19 Best Student Paper Award PAKDD 2022.
2022-03-25 Congratulations! One Chinese Patten is authorized.
2022-01-18 Congratulations! One paper is accepted in IPSN 22.
2022-01-16 Congratulations! One paper is accepted in PAKDD 22.
2021-10-15 Congratulations! One paper is accepted in FPT 21.
2021-02-26 Congratulations! Our work RIIT: Rethinking the Importance of Implementation Tricks in Multi-Agent Reinforcement Learning was shown as a talk in UMD (online).

Selected Publications

JCSC

LiCAM: Long-Tailed Instance Segmentation with Real-Time Classification Accuracy Monitoring

Rongguang Ye, Yantong Guo, Xian Shuai,Rongye Ye, Siyang Jiang^†, Hui Jiang^†

Journal of Circuits, Systems and Computers (SCI), 2022

^† Denotes the corresponding authors.

PDF
CODE

PAKDD

PGADA:Perturbation-Guided Adversarial Alignment for Few-shot Learning Under the Support-QueryShift

Siyang Jiang, Wei Ding, Hsi-Wen Chen, Ming-Syan Chen

Proc. of the 26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD, 2022). Accept rate: 19.30%, 121 out of 627.

Honors and Awards

Best Student Paper Award, PAKDD 2022
Kaggle Competition: Sartorius – Cell Instance Segmentation. Top 4%, Silver Prize
Kaggle Competition: Cassava Leaf Disease Classification. Top 7%, Bronze Prize
National Cryptography Mathematics Challenge, Top 1% Sliver Prize
“KaiLiXin Materials” Scholarship (1/228)
National College Student Business Plan Competition in 2016 Bronze Award

Academic Service

PC/Reviewer as WACV 21, ECML-PKDD 21-22
Session Chair as ECML-PKDD 21

Patent

A Big Data-Based Learning Method for Complex Panel Data (Invention Patent)

Hui Jiang, Bo Liu, Siyang Jiang.
State Intellectual Property Office of the People’s Republic of China,
Patent No.: ZL 2018 1 0343772.3
Patent Application Date: April 17, 2018
Patent Grant Announcement Date: March 25, 2022

Big data intelligent collection and statistical analysis management system(Software Copyright)

Used to collect and analyze large-capacity data which is difficult to capture, manage, and analyze
Computer Software Copyright of China Certification ID: Z2018SR134747