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 Jiefeng Peng

EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation

Sep 16, 2021
Chenhe Dong, Guangrun Wang, Hang Xu, Jiefeng Peng, Xiaozhe Ren, Xiaodan Liang

* Findings of EMNLP 2021 

  Access Paper or Ask Questions

Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift

Aug 22, 2021
Jiefeng Peng, Jiqi Zhang, Changlin Li, Guangrun Wang, Xiaodan Liang, Liang Lin

* Accepted to ICCV 2021 

  Access Paper or Ask Questions

BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

Mar 24, 2021
Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang

* Our searched hybrid CNN-transformer models achieve up to 82.2% accuracy on ImageNet, surpassing EfficientNet by 2.1% with comparable compute time 

  Access Paper or Ask Questions

Blockwisely Supervised Neural Architecture Search with Knowledge Distillation

Nov 29, 2019
Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang

* We achieve a state-of-the-art 78.4% top-1 accuracy on ImageNet in a mobile setting, which is about a 2.1% gain over EfficientNet-B0 

  Access Paper or Ask Questions

Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview

Oct 10, 2018
Lili Huang, Jiefeng Peng, Ruimao Zhang, Guanbin Li, Liang Lin

  Access Paper or Ask Questions

Attentive Crowd Flow Machines

Sep 01, 2018
Lingbo Liu, Ruimao Zhang, Jiefeng Peng, Guanbin Li, Bowen Du, Liang Lin

* ACM MM, full paper 

  Access Paper or Ask Questions

Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches

Feb 28, 2018
Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, Liang Lin

* We presented how to improve and accelerate the training of DNNs, particularly under the context of micro-batches. (Submitted to IJCAI 2018) 

  Access Paper or Ask Questions