Chen He

ABOUT ME

I have recently joined Huawei that is related to Petal Maps. I used to be a PhD student at VIPL-ICT-CAS working on Computer Vision. Take a picture and in no time the computer may tell you what are in the picture and where it happens, even a story about it. Sounds amazing, right? My research topic mainly revolves around Incremental/Lifelong Learning, which endows the algorithm with the ongoing learning ability similar to us humans. The environment is ever-changing, thus the algorithm needs to continually assimilate new knowledge from incoming data. No wonder DARPA says it is the future of AI.

Besides my academic life, I have many hobbies like singing, beatboxing, exercising etc. I'm also a Japanese language learner for over 10 years.

PUBLICATION

Chen He, Ruiping Wang, Shiguang Shan, Xilin Chen. Introspective GAN: Learning to grow a GAN for incremental generation and classification (PR) [Paper][Supp][Code]

Chen He, Ruiping Wang, Xilin Chen. Rethinking Class Orders and Transferability in Class Incremental Learning. Accepted by Pattern Recognition Letters (PRL) [Paper][Supp][Code]

Chen He, Ruiping Wang, Xilin Chen. A Tale of Two CILs: The Connections between Class Incremental Learning and Class Imbalanced Learning, and Beyond. CVPR 2021 Workshop on Continual Learning (best paper) [Paper][Supp][Code]

Chen He, Ruiping Wang, Shiguang Shan, Xilin Chen. Exemplar-Supported Generative Reproduction for Class Incremental Learning. BMVC 2018 [Paper][Supplementary Material][Code]