Minhao Fan

Hi, I'm Minhao Fan. I received my B.S degree in Intelligence Science and Technology from Peking University in 2020. My research mainly focused on Machine Learning related fields including data mining and computer vision. I focus on minimizing the effort required in terms of data, optimization processes, and model deployment around the machine learning pipelines. My ultimate goal is to maximize positive outcomes for society by applying my research to real-world problems at a limited cost. I worked as a research intern at the Spatial and Temporal Restoration Understanding and Compression Team (STRUCT) at WICT under the supervision of Prof. Jiaying Liu. I had also worked with the Data to Knowledge Lab at Rice University supervised by Prof. Xia (Ben) Hu.


Experience

Research Intern at Wangxuan Institute of Computer Technology

Supervised by Prof. Jiaying Liu

A Novel Benchmark for Low-light Enhancement

We present a comprehensive study and evaluation of existing single image low-light enhancement algorithms from the perspective of both human perception and machine vision. Beyond the traditional evaluations in the view of low-level vision, we make the first attempt to set and address a novel task, i.e. face detection in the low-light condition, to explore the potential of benefiting high-level vision tasks with image enhancement methods, both off-line and in an end-to-end manner.

Integrating Semantic Segmentation and Retinex Model for Low-Light Image Enhancement.

Based on the observation that various objects and backgrounds have different material, reflection and perspective attributes, regions of a single low-light image may require different adjustment and enhancement regarding contrast, illumination and noise. We propose an enhancement pipeline with three parts which effectively utilize the semantic layer information. Specifically, we extract the segmentation layer as well as the reflectance, and illumination, and concurrently enhance every separate region, i.g. sky, ground and objects for outdoor scenes.

September 2017 - June 2020

Professional Experiences

Intern of Machine Learning Algorithms

4Paradigm, Beijing

Applying Graph Neural Networks to Sales Volume Forecasting

Intern Researcher of Computer Vision

SenseTime, Shanghai

Portrait Matting on Mobile Devices: Towards App development with limited memory

Software Engineer

Chenyan Technology Co., Shanghai

Leaded the development of intelligent engineering design powered by artiffcial intelligence.

September 2020 - June 2023

Education

Peking University

Bachelor of Science
Department of Machine Intelligence
September 2016 - June 2020

Publications

Minhao Fan, Wenjing Wang, Wenhan Yang, & Jiaying Liu. Integrating Semantic Segmentation and Retinex Model for Low-Light Image Enhancement. ACM International Conference on Multimedia (ACM MM), 2020.

Jiaying Liu, Dejia Xu, Wenhan Yang, Minhao Fan, & Haofeng Huang. Benchmarking Low-Light Image Enhance-ment for Human Perception and Machine Intelligence. International Journal of Computer Vision (IJCV), 2020.


Course Projects

Ataxx Bot

I developed a bot using greedy algorithm for the game of Ataxx on Botzone in the course 'Introduction to Computation'.

The Strongest Projectile

This project includes a simulation program of a WeChat game : ‘The Strongest Projectile’. Also, we wrote a DQN algorithm which taught the agent to play the game. (Ref: https://github.com/RuntianZ/IRL)

Group Based File Management System

A simple file server which enables users to manage their files as well as setup groups with friends for file sharing. (Ref: https://github.com/XFW-go/PKU-Web-Project)


Awards & Certifications

  • May 4th Schorlarship, Peking University, 2017
  • Third Prize in the 16th Annual ACM Competition at Peking University, 2017
  • Third Prize in the 17th Annual ACM Competition at Peking University, 2018
  • A Low-Illumination Face Detection Method Based on Multi-Feature Fusion and A Low-Illumination Face Detection Network, Jiaying Liu, Dejia Xu, Wenhan Yang, Minhao Fan. (IPC publication G06K 9/00, Application number 201910813847.4, Peking University) 2019

Skills

Programming Languages & Tools
  • Python
  • C++
  • HTML/CSS/JavaScript
  • Tensorflow
  • Pytorch