About Me

I am an Applied Scientist at Amazon AWS AI lab. My current research interests lie in Computer Vision and Deep Learning, especially transfer learning, out-of-domain generalization/detection, and etc.

I received my Ph.D degree from ECE Department, College of Engineering, Northeastern University, supervised by  Prof. Raymond Fu.  Prior to NEU, I obtained my Master degree at the Department of ECE, Carnegie Mellon University. During my master study, I worked with Prof. Min Xu at School of Computer Science and Dr.Christoph Mertz at Robotics Institute. Before joining CMU, I received my B.S. degrees in Electrical Engineering from the Huazhong University of Science and Technology. 

Research Interest

• Responsible AI in Multi-modal Large Language Model

• Transfer learning, OOD Generalization, Parameter Efficient Finetuning

• Anomaly Detection and OOD Detection

News

• 2023.11: One paper is  accepted by IJCV 2023

• 2023.7: One paper is accepted by ACM Multimedia 2023

• 2023.3: One paper is accepted by CVPR 2023

• 2023.1: Two papers are accepted by ICLR 2023 (Including one as Oral)

• 2022.5: One paper is accepted by TOMM 2021

• 2022.4: One paper is accepted by IJCAI 2022

• 2022.3: One paper is accepted by CVPR 2022

• 2022.2:  Start summer intern at Amazon  in Seattle 

• 2021.12: One paper is accepted by SDM 2022

• 2021.7: One paper is accepted by ICCV 2021

• 2021.7: One paper is accepted by ACM Multimedia 2021

• 2020.2: Start summer intern at NEC in  San Jose  Remotely

• 2020.2:  One paper is accepted by CVPR 2020 as Oral

• 2019.5:  Start summer intern at Microsoft Research in Seattle 

• 2019.1:  join SMILE LAB, Northeastern University as a PhD student in 2019 Spring

Publication

• Chang Liu*, G. Mittal*, N. Karianakis, V. Fragoso, Ye Yu, Y. Fu, M. Chen. HyperSTAR: Task-Aware Hyperparameter Recommendation for Training and Compression, International Journal of Computer Vision (IJCV), 2023

• Chang Liu, Lichen Wang, and Yun Fu, “Rethinking Neighborhood Consistency Learning on Unsupervised Domain Adaptation,” ACM Multimedia (MM), 2023 [code]

• Yitian Zhang, Yue Bai, Chang Liu, Huan Wang, Sheng Li, Yun Fu, Frame Flexible Network, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023

• Chang Liu, Kunpeng Li, Michael Stopa, Jun Amano, and Yun Fu, Discovering Informative and Robust Positives for Video Domain Adaptation, International Conference on Learning Representations(ICLR), 2023.

• Xu Ma, Yuqian Zhou, Huan Wang, Can Qin, Bin Sun, Chang Liu, and Yun Fu, Image as Set of Points,  International Conference on Learning Representations(ICLR), 2023.

• Kunpeng Li, Chang Liu, Michael Stopa, Jun Amano, Yun Fu, Guided Graph Attention Learning for Video-Text Matching, Transactions on Multimedia Computing Communications and Applications (TOMM) 2021

• Xingchen Zhao, Chang Liu, Anthony Sicilia, Seong Jae Hwang, Yun Fu, Test-time Fourier Style Calibration for Domain Generalization, International Joint Conference on Artificial Intelligence (IJCAI) 2022

• Chang Liu, Xiang Yu, Yi-Hsuan Tsai, Masoud Faraki, Ramin Moslemi, Manmohan Chandraker, Yun Fu, Learning to Learn across Diverse Data Biases in Deep Face Recognition, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022

• Chang Liu, Lichen Wang, Yun Fu. Meta Adversarial Weight for Unsupervised Domain Adaptation, SIAM International Conference on Data Mining (SDM) 2022

• Kai Li, Chang Liu, Handong Zhao, Yulun Zhang, Yun Fu. ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation, International Conference on Computer Vision (ICCV) 2021. 

• Chang Liu, Lichen Wang, Kai Li, Yu Fu. Domain Generalization via Feature Variation Decorrelation, ACM International Conference on Multimedia (MM) 2021.

• Chang Liu*, G. Mittal*, N. Karianakis, V. Fragoso, M. Chen, Y. Fu.  Hyper-STAR: Task-Aware Hyperparameters for Deep Networks, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020 ( * Equal contribution)

• Chang Liu, Zeng X, Wang K, Guo Q, Xu M. Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography. British Machine Vision Conference (BMVC) 2018 : arXiv:1805.06332[PDF]

• Chang Liu, Zeng X, Lin R, Liang X, Freyberg Z, Xing E, Xu M. Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms. IEEE International Conference on Image Processing (ICIP) 2018:  arXiv:1802.04087 [PDF]

Activities

• Reviewer for  ICCV23, CVPR23, IJCAI23, ICLR23, JMLR23, TNNLS2022, AAAI2023, NeuIPS2022, ECCV2022, CVPR 2022, FG2021, ICCV21, AAAI 2021, TIP 2021, AAAI 2020, TKDD2020