diff --git a/README.md b/README.md index 88a5c41..5fe49c8 100644 --- a/README.md +++ b/README.md @@ -5,4 +5,17 @@ To avoid writing the same person, please report the person's name in https://docs.google.com/spreadsheets/d/153XruMO7DPONzBTkxh8ZoYSto1E_2zO021vs0prWZ_Q/edit?usp=sharing First come first serve! ------- -Write here +## Introduction - Henghuang Zhao + + Henghuang Zhao is currently a Ph.D student in Computer Science and Engineering Department, The Chinese University of Hong Kong(CUHK). And his research interest includes computer vision and deep learning. + +## About his work & publications +### 1. ICNet for Real-Time Semantic Segmentation on High-Resolution Images +![](https://hszhao.github.io/projects/icnet/figures/icnet.png) +![ICNet](https://arxiv.org/abs/1704.08545) provide in-depth analysis of their framework and introduce the cascade feature fusion to quickly achieve high-quality segmentation. Their system yields `inference` on a single GPU card with decent quality results evaluated on challenging Cityscapes dataset. +### 2. Pyramid Scene Parsing Network +![](https://hszhao.github.io/projects/pspnet/figures/pspnet.png) +***IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017*** +![PSPNet](https://arxiv.org/abs/1612.01105) came first in ImageNet 2016 scene parsing challenge, PASCAL VOC 2012 benchmark and Cityscapes benchmark. A single PSPNet yields the new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes. + +