Learning and Vision Lab, ECE, NUS
Our lab members, including Tao Wang, Yu Li, Bingyi Kang, Jun Hao Liew, Sheng Tang, and Jiashi Feng, won the 1st Place Entry award at the 1st ICCV 2019 COCO Large Vocabulary Instance Segmentation (LVIS) Challenge at 10/27/2019 at Seoul, Korea.
A classification calibration method for long-tail instance segmentation was proposed to improve the inaccurate proposal classification for tail classes. The authors calibrate the prediction of classification head with a specifically designed twin head which is trained with proposal-level class balance sampling strategy. Without much additional cost and modification, this method improves the performance of baseline by a large margin on tail classes. Our team is one of the co-winners of the challenge, and we surpass the runner-up team by 2.7% in mAP.
Corresonding tech report has been posted on https://arxiv.org/abs/1910.13081, with an improved version submitted to CVPR 2020. See https://www.lvisdataset.org/challenge for more details. [23/11/2019]
Our lab members won the "Best Student Paper Award" at the 26th ACM International Conference on Multimedia which was held during 22-26 Oct, 2018, at Seoul, Republic of Korea. The awarded work by Jian Zhao, Jianshu Li, Yu Cheng, Terence Sim, Shuicheng Yan, Jiashi Feng was titled "Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing". Congratulations!
Attached are Zhao Jian and Jianshu giving presentation at the conference (image 1) and them receiving the award with Jiashi (image 2). See image in new tab to zoom in. [30/10/2018]
Dr. Feng Jiashi, Head of our lab, has been listed as one of the ten young outstanding innovators from the Asia Pacific region (Southeast Asia, Australia, New Zealand and Taiwan) on the MIT Technology Review's "Innovators Under 35" Asia 2018 list.
Dr Feng will automatically become a candidate and potential finalist for the global "Innovators Under 35" list celebrated in the fall of 2018 in Boston, USA. He will deliver a three-minute presentation at EmTach Asia in Singapore on 30-31 January 2018.
See EmTech ASIA homepage; report of ECE, NUS. [24/11/2017]