HOU Yuenan (侯跃南)

I am a 3rd-year PhD candidate at the Department of Information Engineering, the Chinese University of Hong Kong. I am working in the Multimedia Lab, under the supervision of Prof. Chen Change Loy and Prof. Xiaoou Tang.

I received my B.E degree from Nanjing University in July 2017, supervised by Prof. Chunlin Chen and Prof. Xianzhong Zhou. After that, I worked with Dr. Chunxiao Liu and Dr. Zheng Ma during my internship at Sensetime Research.

Currently, I am working in the project of road marking segmentation and knowledge distillation. My research interests include semantic segmentation, knowledge distillation, reinforcement learning and robotic manipulation.

Email / LinkedIn / Google Scholar / Github

  • One paper is accepted by ICCV 2019! (2019-07-23) NEW!

  • One paper is accepted by AAAI 2019 as Oral! (2018-11-23)


Aug. 2017 - Jul. 2021 (Expected), Department of Information Engineering, the Chinese University of Hong Kong ,

Doctor of Philosophy, Information Engineering.


Sep. 2013 - Jul. 2017 , Department of Automation, Nanjing University ,

Balchlor of Engineering, Automation.


Learning Lightweight Lane Detection CNNs by Self Attention Distillation
Yuenan Hou, Zheng Ma, Chunxiao Liu, Chen Change Loy
International Conference on Computer Vision (ICCV), 2019
[pdf] [code]

We present a novel knowledge distillation approach, i.e., Self Attention Distillation (SAD), which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels.


Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks
Yuenan Hou, Zheng Ma, Chunxiao Liu, Chen Change Loy
AAAI Conference on Artificial Intelligence (AAAI, oral), 2019
[pdf] [project page] [code] [ppt] [notes] [first year thesis]

We considerably improve the accuracy and robustness of our steering angle predictive model by distilling multi-layer knowledge from multiple heterogeneous auxiliary networks.


A Novel DDPG Method with Prioritized Experience Replay
Yuenan Hou, Lifeng Liu, Qing Wei, Xudong Xu, Chunlin Chen
IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2017
[pdf] [code] [notes] [bachelor thesis]

We proposed a prioritized experience replay method for the DDPG algorithm, where prioritized sampling is adopted instead of uniform sampling.


Agnostic Lane Detection
Yuenan Hou
arXiv preprint arXiv:1905.03704, 2019
[pdf] [code]

We released a lightweight lane detection model, i.e., ENet-label, which can detect an arbitrary number of lanes and extremely thin lanes at 50 fps in theory.

  • Road Marking Segmentation, Jun. 2019 - Now

Selected course work
Academic Services
  • Research Assistant for Information Engineering, 2017, 2018

Honors and Awards
  • Postgraduate Scholarship, the Chinese University of Hong Kong, 2017 ~ now

  • Third Prize of Jiangsu Province for Undergraduate Thesis, Nanjing University, 2017 [paper pdf] [awards list]

  • Zhenggang Scholarship, Nanjing University, 2017

  • Mathematical Contest in Modeling (MCM), Meritorious Winner (13%), 2016 [paper pdf]

  • Liao's Scholarship, Nanjing University, 2015

  • National Scholarship, Nanjing University, 2014