Team DoubleY from UTAR secured first place in the prestigious IEEE BigData Cup 2024: Building Extraction Generalization Challenge, showcasing outstanding expertise in data science and deep learning. The online competition, held from 27 May to 1 September 2024, concluded with an award ceremony on 16 December 2024 during the IEEE International Conference on Big Data at the Hyatt Regency Washington on Capitol Hill, Washington, DC, USA. The conference was organised in a hybrid format, allowing both in-person and online participation.
The team consisted of Wong Yi Jie, a Year 2 PhD (Engineering) student from the Lee Kong Chian Faculty of Engineering and Science (LKC FES), and UTAR alumnus Khor Yin Loon. They were mentored by LKC FES academics Assoc Prof Ir Ts Dr Tham Mau Luen, Assoc Prof Dr Kwan Ban Hoe, Department of Electrical and Electronic Engineering Head Ir Prof Dr Chang Yoong Choon, and Prof Anissa Mokraoui from Université Paris 13. Wong and Khor received their certificate and presented their winning solution virtually. Their innovative solution for improving the generalisation of building footprint extraction algorithms using satellite imagery earned them the top spot.
The conference was organised in a hybrid format, allowing both in-person and online participation.
The challenge aimed to address the complexities of building extraction, including variations in size, shape, and regional differences by leveraging a Tokyo-based training dataset and testing in other Japanese regions. Hosted on the Kaggle platform, the competition received 263 code submissions from 68 global entrants over four months, with only 19 participants securing a leaderboard position. The top five teams, ranked by the AI evaluation metric F1 Score, were invited to submit a paper to the 2024 IEEE International Conference on Big Data under the BigData Cup Challenges track. Among the five submissions, only three papers were accepted.
The UTAR team secured first place and presented their paper “Cross-City Building Instance Segmentation: From More Data to Diffusion-Augmentation” at IEEE BigData 2024 on 16 December 2024. The USA team from the Big Data Analytics Solutions Lab., R&D Department of Hitachi America, Ltd., achieved second place, while the Taiwan team from Feng Chia University secured third place.
Reflecting on their achievement, they shared, “The recognition from the IEEE BigData Cup 2024 challenge is significant to us. It enhances our academic and professional credentials by showcasing our ability to address complex problems using advanced data science techniques. Additionally, the challenge is part of the prestigious IEEE International Conference on Big Data, which highlights our skills in data science. We are delighted to be one of the invited teams to contribute a paper for the conference on our proposed method for the challenge.”
The team’s outstanding performance not only earned them USD1,000, a trophy, and certificates but also established UTAR as a leader in innovative data science solutions on an international platform.
The certificate won by Team DoubleY
© 2025 UNIVERSITI TUNKU ABDUL RAHMAN DU012(A).
Wholly owned by UTAR Education Foundation (200201010564(578227-M)) LEGAL STATEMENT TERM OF USAGE PRIVACY NOTICE
