Biography and Contact

I am a Ph.D. student of Faculty Information Technology at Monash University, Australia. 

I am supervised by Asst. Prof. Bohan Zhuang, Prof. Jianfei Cai, and Prof. Chunhua Shen.

My main research topic is efficient deep models for resource-constrained edge devices. 

Here is my CV and google scholar. 

I'm looking for a research internship. If you are interested in my research, please drop me an email.

Github: https://github.com/liujingcs.

Email: liujing_95@outlook.com. 

News

• 2023.03: One paper is accepted by CVPR 2023!

• 2022.11: Ecoformer will be presented as Spotlight!

• 2022.09: One first-author paper is accepted by NeruIPS 2022!

• 2022.07: Invited to serve as a reviewer for ICLR 2023!

• 2022.03: Invited to serve as a reviewer for NeurIPS 2023!

Publications

(* indicates equal contributions)

• Dynamic Focus-aware Positional Queries for Semantic Segmentation

Haoyu He, Jianfei Cai, Zizheng Pan, Jing Liu, Jing Zhang, Dacheng Tao, Bohan Zhuang

Conference on Computer Vision and Pattern Recognition (CVPR), 2023

[arxiv][code]

• EcoFormer: Energy-Saving Attention with Linear Complexity

Jing Liu, Zizheng Pan*, Haoyu He, Jianfei Cai, Bohan Zhuang

Neural Information Processing Systems (NeurIPS Spotlight), 2022

[arxiv][code]

• Sharpness-aware Quantization for Deep Neural Networks

Jing Liu, Jianfei Cai, Bohan Zhuang

[arxiv][code]

• Pruning Self-attentions into Convolutional Layers in Single Path

Haoyu He, Jing Liu, Zizheng Pan, Jianfei Cai, Jing Zhang, Dacheng Tao, Bohan Zhuang

[arxiv][code]

• Mesa: A Memory-saving Training Framework for Transformers

Zizheng Pan, Peng Chen, Haoyu He, Jing Liu, Jianfei Cai, Bohan Zhuang

[arxiv][code]

• Elastic Architecture Search for Diverse Tasks with Different Resources

Jing Liu, Bohan Zhuang, Mingkui Tan, Xu Liu, Dinh Phung, Yuanqing Li, Jianfei Cai

[arxiv]

• Less is More: PayLess Attentionin VisionTransformers

Zizheng Pan, Bohan Zhuang, Haoyu He, JingLiu, Jianfei Cai

AAAI Conference on Artificial Intelligence (AAAI), 2022

[arxiv][code]

• Scalable Visual Transformers with Hierarchical Pooling

Zizheng Pan, Bohan Zhuang, Jing Liu, Haoyu He, Jianfei Cai

International Conference on Computer Vision (ICCV), 2021

[arxiv][code]

• Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations 

Bohan Zhuang*, Mingkui Tan*, Jing Liu*, Lingqiao Liu, Ian Reid, Chunhua Shen

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

[arxiv] [code] 

• Discrimination-aware Network Pruning for Deep Model Compression

Jing Liu*, Bohan Zhuang*, Zhuangwei Zhuang*, Yong Guo, Junzhou Huang, Jinhui Zhu, Mingkui Tan

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

[paper][code]

• LBS: Loss-aware Bit Sharing for Automatic Model Compression

Jing Liu, Bohan Zhuang, Peng Chen, Yong Guo, Chunhua Shen, Jianfei Cai, Mingkui Tan

[arxiv]

• AQD: Towards Accurate Quantized Object Detection

Peng Chen, Jing Liu*, Bohan Zhuang, Mingkui Tan, Chunhua Shen

Conference on Computer Vision and Pattern Recognition (CVPR Oral), 2021

[arxiv][code]

• Deep Transferring Quantization

Zheng Xie*, Zhiquan Wen*, Jing Liu*, Zhiqiang Liu, Xixian Wu, Mingkui Tan

European Conference on Computer Vision (ECCV), 2020

[paper][code]

• Generative Low-bitwidth Data Free Quantization

Shoukai Xu*, Haokun Li*, Bohan Zhuang*, Jing Liu, Jiezhang Cao, Chuangrun Liang, Mingkui Tan 

European Conference on Computer Vision (ECCV), 2020

[paper][code]

• Discrimination-aware Channel Pruning for Deep Neural Networks

Zhuangwei Zhuang*, Mingkui Tan*, Bohan Zhuang*, Jing Liu*, Yong Guo, Qingyao Wu, Junzhou Huang, Jinhui Zhu

Neural Information Processing Systems (NeurIPS), 2018 

[paper][code]

Professional Services

• Conferences: CVPR (2023), ICLR (2023), NeurIPS (2022), ECCV (2022), ICML (2022), CVPR (2022), NeurIPS (2021), ICLR (2022), MICCAI (2019)

• Journals: IJCV (2022), TPAMI (2022), TPAMI (2021)

Awards and Scholarships

• NeurIPS 2021 Outstanding Reviewer

• Faculty of Information Technology Research Scholarship

Thanks for your attention !