Zhengbo Zhang | 张正博
My research focuses on generative models (such as diffusion models for video generation and editing)
and reinforcement learning. Previously, I also conducted research in the field of model
compression.
Email /
Google Scholar /
GitHub
|
|
Selected publications
|
|
|
|
|
|
|
Distilling Inter-Class Distance for Semantic Segmentation
Zhengbo Zhang, Chunluan Zhou, Zhigang Tu
IJCAI (Long Oral), 2022
paper
We propose a novel knowledge distillation method for semantic segmentation that encourages the student model to achieve large inter-class distances in the feature space, thereby enhancing segmentation accuracy.
|
|
Instance Temperature Knowledge Distillation
Zhengbo Zhang, Yuxi Zhou, Jia Gong, Jun Liu, Zhigang Tu,
ArXiv Preprint, 2023
project page / paper / code
We formulate the allocation of instance-specific temperatures in knowledge distillation as a sequential decision-making task and propose a novel reinforcement learning-based method, RLKD, to address it.
|
This homepage is designed based on Jon Barron's website. Last updated: Mar. 11, 2025
|