Gim Hee Lee

Gim Hee Lee

Auto-generated profile, based on publicly available information

Gim Hee Lee

National University of Singapore

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications

10 June 2019 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
SHSixing Hu
Sixing Hu
GLGim Hee Lee
Gim Hee Lee

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
NDNa Dong
Na Dong
YZYongqiang Zhang
Yongqiang Zhang
MDMingli Ding
Mingli Ding
GLGim Hee Lee
Gim Hee Lee
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object detection that rely on the availability of abundant training samples per novel class that substantially limits the scalability to real-world setting where novel data can be scarce. In this paper, we propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector. To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision from additional object proposals generated using Selective Search as pseudo labels. We further introduce an incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without forgetting the base classes. Extensive experiments conducted on standard incremental object detection and incremental few-shot object detection settings show that our approach significantly outperforms state-of-the-art methods by a large margin. Our source code is available at https://github.com/dongnana777/Incremental-DETR.

18 October 2023 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YZYuyang Zhao
Yuyang Zhao
Zhun ZhongZhun Zhong
Zhun Zhong
NZNa Zhao
Na Zhao
NSNicu Sebe
Nicu Sebe
GLGim Hee Lee
Gim Hee Lee

6 November 2022
Verified
Book Chapter
Closed access
PDF file
HSHualian Sheng
Hualian Sheng
SCSijia Cai
Sijia Cai
NZNa Zhao
Na Zhao
BDBing Deng
Bing Deng
JHjianqiang huang
jianqiang huang
GLGim Hee Lee
Gim Hee Lee

30 September 2024
Verified
Book Chapter
Closed access
PDF file
Yan LiYan Li
Yan Li
CLChenyu Lyu
Chenyu Lyu
YDYan Di
Yan Di
GZGuangyao Zhai
Guangyao Zhai
GLGim Hee Lee
Gim Hee Lee
FTFederico Tombari
Federico Tombari