Bio

This is Xiang Deng, PhD from State University of New York at Binghamton with advisor Prof. Zhongfei Zhang. I aim to design simple but very effective deep learning approaches. Simplicity yet effectiveness is the best. My research interests are mainly on multi-models and embodied AI, efficient & effective learning, knowledge distillation & supervised learning, GANs & image processing (e.g., enhancement), and deep metric learning. Prior to joining SUNY-Binghamton, I obtained the Bachelor’s and Master’s degrees from Shandong University in 2015 and 2018, respectively.

News

• [July 2022] One paper accepted by ECCV’2022.
• [May 2022] Join Meta as a research intern
• [May 2022] One paper accepted by ICML’2022
• [Jan 2022] Receive Graduate School Student Excellence Award
• [Dec 2021] One paper accepted by AAAI’2022.
• [Oct 2021] One paper accepted by Neural Networks.
• [Sep 2021] One paper accepted by NeurIPS’2021.
• [Sep 2021] Join JD.com as a reseasrch intern.
• [Apr 2021] One paper accepted by IJCAI’2021.
• [Dec 2020] One paper accepted by AAAI’2021.

Selected Publications Since 2020

• Xiang Deng, Zhongfei Zhang. “Personalized Education: Blind Knowledge Distillation”, 2022 European Conference on Computer Vision (ECCV’2022)

• Xiang Deng, Zhongfei Zhang. “Deep Causal Metric Learning”, Proc. of the 39th International Conference on Machine Learning (ICML’2022)

• Xiang Deng, et al. “Reducing Flipping Errors in Deep Neural Networks”, Proc. of the 36th AAAI Conference on Artificial Intelligence (AAAI’2022)

• Xiang Deng, Zhongfei Zhang. “Comprehensive Knowledge Distillation with Causal Intervention”, Proc. of the 30th Conference on Neural Information Processing Systems (NeurIPS’2021)

• Xiang Deng, Zhongfei Zhang. “Sparsity-Control Ternary Weight Networks”, Neural Networks, 2021

• Xiang Deng, Zhongfei Zhang. “Graph-Free Knowledge Distillation for Graph Neural Networks”, Proc. of the 30th International Joint Conference on Artificial Intelligence (IJCAI’2021)

• Xiang Deng, Zhongfei Zhang. “Learning with Retrospection”, Proc. of the 35th AAAI Conference on Artificial Intelligence (AAAI’2021)

• Xiang Deng, Zhongfei Zhang. “Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?”, Proc. of the 25th International Conference on Pattern Recognition (ICPR’2020)

• to be added

Work Experience

• [03/2023 - present] HIT-SZ
• [05/2022 - 08/2022] Research Intern at Meta (Facebook)
• [05/2021 - 08/2022] Research Intern at JD.com (JingDong)
• [08/2018 - 05/2022] Teaching Assistant at Binghamton University

Professional Service Member

Conference Program Committee

• International Conference on Machine Learning (ICML)
• Conference on Neural Information Processing Systems (NeurIPS)
• IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)
• European Conference on Computer Vision (ECCV)
• AAAI Conference (AAAI)
• International Joint Conference on Artificial Intelligence (IJCAI)
• International Conference on Pattern Recognition (ICPR)
• IEEE International Conference on Data Science and Advanced Analytics (DASS)
• IEEE International Conference on Data Mining (ICDM)

Journal Reviewer

• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
• IEEE Transactions on Multimedia (TMM)
• Journal of Computer Science and Technology (JCST)
• Journal of Electronic Imaging (JEI)

This website was last updated: 09/17/2022 EST

Starting from Jul 20, 2022: