Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Zechun Liu

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

Jan 03, 2022
Arnav Chavan, Zhiqiang Shen, Zhuang Liu, Zechun Liu, Kwang-Ting Cheng, Eric Xing

* Technical report 

  Access Paper or Ask Questions

Data-Free Neural Architecture Search via Recursive Label Calibration

Dec 03, 2021
Zechun Liu, Zhiqiang Shen, Yun Long, Eric Xing, Kwang-Ting Cheng, Chas Leichner

* Technical report 

  Access Paper or Ask Questions

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation

Nov 29, 2021
Zechun Liu, Kwang-Ting Cheng, Dong Huang, Eric Xing, Zhiqiang Shen

* Technical report 

  Access Paper or Ask Questions

Sliced Recursive Transformer

Nov 09, 2021
Zhiqiang Shen, Zechun Liu, Eric Xing

* Code and models are available at 

  Access Paper or Ask Questions

How Do Adam and Training Strategies Help BNNs Optimization?

Jun 21, 2021
Zechun Liu, Zhiqiang Shen, Shichao Li, Koen Helwegen, Dong Huang, Kwang-Ting Cheng

* ICML 2021. Code and models are available at 

  Access Paper or Ask Questions

"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization

Apr 16, 2021
Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, Zhangyang Wang

  Access Paper or Ask Questions

Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study

Apr 01, 2021
Zhiqiang Shen, Zechun Liu, Dejia Xu, Zitian Chen, Kwang-Ting Cheng, Marios Savvides

* ICLR 2021. Project page: 

  Access Paper or Ask Questions

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration

Feb 17, 2021
Zhiqiang Shen, Zechun Liu, Jie Qin, Lei Huang, Kwang-Ting Cheng, Marios Savvides

* Technical report, 10 pages. Self-supervised binary neural networks using distillation loss (5.5~15% improvement over contrastive baseline) 

  Access Paper or Ask Questions

Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning

Feb 08, 2021
Zhiqiang Shen, Zechun Liu, Jie Qin, Marios Savvides, Kwang-Ting Cheng

* AAAI 2021. A search based fine-tuning strategy for few-shot learning 

  Access Paper or Ask Questions

Conditional Link Prediction of Category-Implicit Keypoint Detection

Nov 29, 2020
Ellen Yi-Ge, Rui Fan, Zechun Liu, Zhiqiang Shen

* WACV 2021 paper 

  Access Paper or Ask Questions

Weight-dependent Gates for Network Pruning

Jul 04, 2020
Yun Li, Weiqun Wu, Zechun Liu, Chi Zhang, Xiangyu Zhang, Haotian Yao, Baoqun Yin

* 15 pages, 5 figures 

  Access Paper or Ask Questions

Joint Multi-Dimension Pruning

May 18, 2020
Zechun Liu, Xiangyu Zhang, Zhiqiang Shen, Zhe Li, Yichen Wei, Kwang-Ting Cheng, Jian Sun

  Access Paper or Ask Questions

Binarizing MobileNet via Evolution-based Searching

May 15, 2020
Hai Phan, Zechun Liu, Dang Huynh, Marios Savvides, Kwang-Ting Cheng, Zhiqiang Shen

* Accepted by CVPR2020 

  Access Paper or Ask Questions

Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification

Apr 05, 2020
Devesh Walawalkar, Zhiqiang Shen, Zechun Liu, Marios Savvides

  Access Paper or Ask Questions

Rethinking Image Mixture for Unsupervised Visual Representation Learning

Mar 11, 2020
Zhiqiang Shen, Zechun Liu, Zhuang Liu, Marios Savvides, Trevor Darrell

  Access Paper or Ask Questions

ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions

Mar 07, 2020
Zechun Liu, Zhiqiang Shen, Marios Savvides, Kwang-Ting Cheng

  Access Paper or Ask Questions

Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization

Jun 05, 2019
Koen Helwegen, James Widdicombe, Lukas Geiger, Zechun Liu, Kwang-Ting Cheng, Roeland Nusselder

  Access Paper or Ask Questions

Single Path One-Shot Neural Architecture Search with Uniform Sampling

Apr 06, 2019
Zichao Guo, Xiangyu Zhang, Haoyuan Mu, Wen Heng, Zechun Liu, Yichen Wei, Jian Sun

  Access Paper or Ask Questions

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning

Apr 03, 2019
Zechun Liu, Haoyuan Mu, Xiangyu Zhang, Zichao Guo, Xin Yang, Tim Kwang-Ting Cheng, Jian Sun

  Access Paper or Ask Questions

Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance

Nov 04, 2018
Zechun Liu, Wenhan Luo, Baoyuan Wu, Xin Yang, Wei Liu, Kwang-Ting Cheng

* Submitted to IJCV. It is the journal extension of our ECCV paper: arXiv:1808.00278 

  Access Paper or Ask Questions

Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm

Sep 29, 2018
Zechun Liu, Baoyuan Wu, Wenhan Luo, Xin Yang, Wei Liu, Kwang-Ting Cheng

* Accepted to European Conference on Computer Vision (ECCV) 2018. Code is available on: 

  Access Paper or Ask Questions