Zhihao Duan

Hi! I’m a PhD candidate at Purdue University ECE, the Video and Image Processing Lab. My research lies in the intersection of data compression, computer vision, and machine learning. Our goal is to use deep learning to improve visual data compression (compression using AI) and design compressors tailored to downstream vision tasks (compression for AI). I also worked with colleagues on neural network model compression (compression of AI).

Education: I got my Bachelor’s degree in Electrical Engineering from Shanghai Jiao Tong University, China, in 2018. I got my Master’s degree in ECE from Boston University, USA, in 2020. I’m currently pursuing the PhD degree at Purdue University, USA, and expect to graduate in late 2024.

news

Feb 27, 2024	Our paper “Towards Backward-Compatible Continual Learning of Image Compression” is accepted to CVPR 2024!
Oct 04, 2023	Our paper “QARV: Quantization-Aware ResNet VAE for Lossy Image Compression” is accepted to IEEE TPAMI!
Jan 04, 2023	Our paper “Lossy Image Compression with Quantized Hierarchical VAEs” is awarded the Best Paper Award at WACV 2023!

selected publications

Towards Backward-Compatible Continual Learning of Image Compression

Zhihao Duan, Ming Lu , Justin Yang , Jiangpeng He , Zhan Ma , and Fengqing Zhu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024

arXiv Bib Code

@article{duan2024continual_compression,
  title = {Towards Backward-Compatible Continual Learning of Image Compression},
  author = {Duan, Zhihao and Lu, Ming and Yang, Justin and He, Jiangpeng and Ma, Zhan and Zhu, Fengqing},
  journal = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  month = jun
}

QARV: Quantization-Aware ResNet VAE for Lossy Image Compression

Zhihao Duan, Ming Lu , Jack Ma , Yuning Huang , Zhan Ma , and Fengqing Zhu

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Jun 2024

arXiv Bib Code

@article{duan2024qarv,
  title = {QARV: Quantization-Aware ResNet VAE for Lossy Image Compression},
  author = {Duan, Zhihao and Lu, Ming and Ma, Jack and Huang, Yuning and Ma, Zhan and Zhu, Fengqing},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2024},
  volume = {46},
  number = {1},
  pages = {436-450},
  doi = {10.1109/TPAMI.2023.3322904}
}

Lossy Image Compression with Quantized Hierarchical VAEs

Zhihao Duan, Ming Lu , Zhan Ma , and Fengqing Zhu

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2023

Best Paper Award - Algorithms

arXiv Bib Code

@article{duan2023qres,
  highlight = {<a href="https://wacv2023.thecvf.com/node/174">Best Paper Award - Algorithms</a>},
  title = {Lossy Image Compression with Quantized Hierarchical VAEs},
  author = {Duan, Zhihao and Lu, Ming and Ma, Zhan and Zhu, Fengqing},
  journal = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  pages = {198--207},
  year = {2023},
  month = jan,
  doi = {10.1109/WACV56688.2023.00028}
}

Efficient Feature Compression for Edge-Cloud Systems

Zhihao Duan, and Fengqing Zhu

Picture Coding Symposium, Dec 2022

Best Paper Award Finalists (top 5%)

arXiv Bib Code

@article{duan2022pcs_edge_cloud,
  highlight = {<a href="https://2022.picturecodingsymposium.org/best_paper_award_finalists.php">Best Paper Award Finalists (top 5%)</a>},
  title = {Efficient Feature Compression for Edge-Cloud Systems},
  author = {Duan, Zhihao and Zhu, Fengqing},
  journal = {Picture Coding Symposium},
  year = {2022},
  month = dec,
  pages = {187-191},
  doi = {10.1109/PCS56426.2022.10018075}
}

RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images

Zhihao Duan, M. Ozan Tezcan , Hayato Nakamura , Prakash Ishwar , and Janusz Konrad

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2020

arXiv Bib Code Website

@article{duan2020rapid,
  title = {RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images},
  author = {Duan, Zhihao and Ozan Tezcan, M. and Nakamura, Hayato and Ishwar, Prakash and Konrad, Janusz},
  journal = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  year = {2020},
  month = jun,
  pages = {2700-2709},
  doi = {10.1109/CVPRW50498.2020.00326}
}