yiyuezhang

Congratulations to Eddy Wu for passing his defense. His thesis title is “Deep Learning Techniques for Supervised Pedestrian Detection and Critically-Supervised Object Detection” with three major topics, as follow:

In the first topic, a boosted convolutional neural network (BCNN) system is proposed to enhance the pedestrian detection performance. Being inspired by the classic boosting idea, we develop a weighted loss function that emphasizes challenging samples in training a convolutional neural network (CNN). Two types of samples are considered challenging: 1) samples with detection scores falling in the decision boundary, and 2) temporally associated samples with inconsistent scores. Finally, we train a boosted fusion layer to benefit from the integration of these two weighting schemes. We test the corresponding BCNN on the Caltech pedestrian dataset in the experiment and observe a significant performance gain over the Fast-RCNN baseline.

In the second topic, a semi-supervised learning method is proposed for pedestrian detection in a domain adaptation setup. The proposed clustered deep representation adaptation (CDRA) method uses a small amount of labeled data to train an intial detector, extracts the deep representation and, then, clusters samples based on the space spanned by the deep representation. A purity measurement mechanism is applied to each cluster to provide a confident score to the estimated class of unlabeled data. Along with a weighted training approach, the CDRA method is shown to achieve the state-of-the-art performance against some large scale datasets.

In the third topic, we propose a new framework called critically-supervised learning that mimics children learing behaviors. Several novel components are proposed to fulfill the high level concept, including negative object proposal, critical example mining, and a machine-guided labeling process based on question answering. A labeling time model is proposed to [...]

We are so happy to welcome a new summer intern student, Zhichao Huang, in Summer 2017. Let us hear what he said about his research and MCL.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

I’m Zhichao Huang, a junior student from Tsinghua University, majoring Electronic Engineering. Although I came from EE department, the research that I have done is mainly in the field computer science. I have been working on the area of computer vision for about one year, focusing on face recognition, person identification and something like that. In addition to computer vision, I also worked on some small project in the course that I took like web scrapping, digital circuits etc.

2. What’s your first impression of USC and MCL?

This is the first time that I came to USC and I’m deeply impressed by its architecture, atmosphere and people. The buildings have a very different style from those in the campus of China, seems to tell a long story about the school. People here are very friendly. They give us a warm welcome, leading us around campus, treating us with delicious food and answering every question patiently.

MCL is a great lab with wonderful atmosphere. Professor Kuo treat us with a wonderful meal and ask our interest specifically. And everyone is willing to help each other, discussing the project, answering every quesion when we are in need. I do have a great time in MCL.

3. What’s your future expectation for MCL?

I hope to make progess in the current project that I am working on and learn more about computer vision.

We are so happy to welcome a new summer intern student, Jeffrey Maierhofer, in Summer 2017. Let us hear what he said about his research and MCL.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

My name is Jeffrey “Matt” Maierhofer. I am currently an undergraduate student at the University of Colorado Boulder studying Applied Mathematics and Computer Science. In the past I have done some research in numerical solvers for complex differential equations. I am also interested in applications of mathematics that involve a heavy combination of computer science and mathematics.

2. What’s your first impression of USC and MCL?

My first impression of USC was how beautiful the campus was. The weather has been wonderful, and the campus itself is really pleasing to walk through. MCL is by far the largest research group that I’ve ever been a part of, and i really like how it promotes collaboration within the lab.

3. What’s your future expectation for MCL?

I hope to learn as much as possible during my summer in MCL and hope to get to know a lot of cool people!

We are so happy to welcome a new summer intern student, Sreedhar Radhakrishnan, in Summer 2017. Let us hear what he said about his research and MCL.

1. Could you briefly introduce yourself? (Previous research experience, project experience, research interest and expertise)

Hi, I am Sreedhar, I am currently an undergrad senior in Computer Science and Engineering at PES University,Bangalore,India and Data Science excites me. After my freshman year I interned at a research centre at my university where I was introduced to methodologies of research and I worked in the area of Computer Vision. The following year I had coursework in Design and Analysis of Algorithms and Linear Algebra which I fell in love with as I was able to get a perspective of how they are used in real world problems based on my research after my freshman year. The summer after sophomore year I worked on data analysis applied in the sport of Cricket and developed a player evaluation metric through the same. This really got me interested in leveraging the power of data in numerous applications. I then had course work in Data Analytics, Natural Language Processing, Digital Image Processing and Big Data which are some of my favorite courses. I am currently interested in Machine Learning and Deep Learning and their applications in various fields such as Computer Vision and NLP. I am currently working on Deep Learning for Computer Vision and learning a lot under the guidance of Dr. Kuo and fellow MCL members.

2. What’s your first impression of USC and MCL?

I just completed my first week of the summer internship here and I love the environment. Members of MCL are truly very hard working and dedicated in their [...]