weiwang

Welcome New MCL Member Tian Xie

We are so glad to welcome our new MCL member, Tian Xie! Here is a short interview with Tian:

1. Could you briefly introduce yourself and your research interests?

My name is Tian Xie, and I am a third-year Ph.D. student at MCL lab in the department of Electrical Engineering at USC. Prior to joining MCL, I was a Ph.D. student at the InfoLab of USC. I received my Bachelor’s degree in mathematics from Fudan University of China. I am interested in representation learning and deep learning. Previously I worked on research projects related to graph and adversarial learning.

2. What is your impression about MCL and USC?

USC is a small but beautiful campus. I really enjoy walking around the campus and having some coffee around the school cafe. The MCL lab is a wonderful place with a caring and supportive advisor and a large group of young talented students. I feel more motivated and enthusiastic about my research after joining MCL and I really enjoy talking with Professor Kuo since he is a really wise person.

3. What is your future expectation and plan in MCL?

I want to make friends in MCL, do good research and write papers. Hopefully, my research can contribute to the progress of the related field.

By |February 17th, 2020|News|Comments Off on Welcome New MCL Member Tian Xie|

Welcome New MCL Member Yuhang Xu

We are so glad to welcome our new MCL member, Yuhang Xu! Here is a short interview with Yuhang:

1. Could you briefly introduce yourself and your research interests?

My name is Yuhang Xu. I am a graduate student at USC pursuing a MS degree in Electrical Engineering. My research interests include machine learning and image processing. Recently, I am working on a neural network compression project under the supervision of Prof. Kuo. In my free time I enjoy reading news from around the world, listening to country music, and cooking Chinese food.

2. What is your impression about MCL and USC?

MCL is a mature research group with more than 20 passionate and hardworking individuals. It is prolific and well-organized under the supervision of Prof. Kuo. Prof. Kuo is filled with knowledge and is an inspiration to his students. USC is the perfect balance of academic and social opportunities. During my time at USC, I make friends with people from different cultures.

3. What is your future expectation and plan in MCL?

My short-term goal is to complete the current project. It is an interesting one and it has special meaning for me since it is my first project in MCL. I also hope to create strong connections with people in the lab.

By |February 7th, 2020|News|Comments Off on Welcome New MCL Member Yuhang Xu|

Welcome New MCL Member Zohreh Azizi

We are so glad to welcome our new MCL member, Zohreh Azizi! Here is a short interview with Zohreh:

1. Could you briefly introduce yourself and your research interests?

My name is Zohreh Azizi. I am a PhD student in Electrical Engineering. Before joining USC, I did my bachelors in Sharif University of Technology, Iran. Previously, my research experience was focused on designing biomedical devices. While developing software for devices, I became more familiar with AI, Machine learning, and topics like computer vision, which I found really interesting. I appreciate Prof. Kuo for giving me the chance to join MCL and have the opportunity to explore my interest.

2. What is your impression about MCL and USC?

I can’t believe how every single member in MCL is so nice and helpful. They all work hard and behave in a professional manner. There is so much for me to learn from everyone in MCL, and especially from Prof. Kuo, who is really caring, motivating, and hardworking. USC has a beautiful campus and a lively environment.

3. What is your future expectation and plan in MCL?

I have lots of things to learn. I am so excited to work hard and gain more skills and explore new ideas. I would like to solve significant problems in computer vision and machine learning. I hope that I can contribute to MCL both by my research and by helping my fellow mates.

By |February 2nd, 2020|News|Comments Off on Welcome New MCL Member Zohreh Azizi|

MCL Research on Graph Embedding

Graph is a data representation model. Each data point is considered as a node and an edge/connection exists between nodes if there is any common characteristics. The relationship that exists between nodes is complex and attracts research in this domain. Several techniques have been developed like Deep Walk, Planetoid, Chebyshev, Graph Convolution Network, Graph Attention Network, Large Scale Graph Convolution Network, and so on, which focuse on exploring the behavior of the nodes based on their connectivity to different nodes. Graph models are often designed for tasks like Node classification, Edge/Link prediction, and has varied applications in social network, citation networks.

Currently we are developing a Graph Neural Network model for node classification task of a Graph. Feedforward based approach is adopted to learn the network parameters in a single forward pass using Graph Hop Method. The main idea is to learn the node’s representation making use of their hop’s (neighboring node’s) representation to better represent and learn from local to global attribute perspective through information exchange between the hops, by subsequently growing the dimension of the feature vector and reducing the dimensionality using SaaB transform.

Unlike the methods/techniques which are already developed, our model’s computational complexity is very low for the fact that no back propagation is utilized for learning the parameters of the network model, but through feedforward design the model learns in a single forward pass. The Graph Hop Method serves as a unique method for driving the model to train on very less training samples yet provide better accuracies/results for testing samples. Thus, the model is capable to train on very limited labelled data. Making use of only 5% of training samples, we are able to achieve the state of art performance [...]

By |September 8th, 2019|News|Comments Off on MCL Research on Graph Embedding|

MCL Research on Image-based Object Recognition

The subspace technique has been widely used in signal/image processing, pattern recognition, computer vision, etc. It may have different definitions in different contexts. A subspace may denote a dominant feature space where less relevant features are dropped. One example is the principal component analysis (PCA). A subspace may also refer to a certain object class such as the subspace of digit “0” in the MNIST dataset.  Generally speaking, subspace methods offer a powerful and popular tool for signal analysis, modeling and processing.  They exploit statistical properties of a class of underlying signals so as to determine a smaller yet significant subspace for further processing.

However, existing subspace methods are conducted in a single stage.  We may wonder whether there is any advantage to perform subspace methods in multiple stages. Research on generalizing from one-stage subspace methods to multi-stage subspace methods is actually rare.  Two PCA stages are cascaded in a straightforward manner in the PCAnet[1]. Being motivated by multiple convolutional layers in convolutional neural networks (CNNs), Prof. Kuo proposed a new machine learning paradigm, called successive subspace learning (SSL). It has multiple subspace modules in cascade by mimicking the feedforward CNN operations, and the parameters of subspace transformation are learned from the training data.  Although there is a strong similarity between the feedforward paths of CNNs and the SSL approach, they are fundamentally different in the machine learning model formulation, the training process and complexity.

To illustrate the SSL approach furthermore, Yueru Chen and Prof. Kuo proposed a PixelHop method based on SSL for image-based object recognition. It consists of three steps: 1) local-to-global attributes of images are extracted through multi-hop information exchange, 2) subspace-based dimensionality reduction (SDR) is adopted to new image representation from each [...]

By |September 2nd, 2019|News|Comments Off on MCL Research on Image-based Object Recognition|

MCL Research on Texture Analysis & Modeling

Texture is a one of the most fundamental yet important characteristic of images, and texture analysis & modeling is an essential and challenging problem in computer vision and pattern recognition, which has attracted extensive research attention over the last several decades.

As a powerful visual cue, texture play an important role in human perception, and provides useful information in identifying objects or regions in images, ranging from multispectral satellite data to microscopic images of tissue samples. Besides, understanding texture is also a key component in many other computer vision topics, including image de-noising, image super-resolution and image generation.

In the past few years, MCL has done original research works in several important aspects of texture analysis & modeling, including texture representation, unsupervised texture segmentation, and dynamic texture synthesis.

Texture Representation[1]: A hierarchical spatial-spectral correlation (HSSC) method is proposed for texture analysis in this work. The HSSC method first applies a multi-stage spatial-spectral transform to input texture patches, which is known as the Saak transform. Then, it conducts a correlation analysis on Saak transform coefficients to obtain texture features of high discriminant power. During the correlation analysis, both auto-correlation and cross-correlation are computed, and further used to get compact and representative feature for texture. Given the fact that texture is the spatial organization of a set of basic patterns, we further provide theoretical explanation of proposed method, that it attempts to capture the energy distribution of orthogonal texture patterns derived from the Saak transform. This paper has been accepted by ICIP2019.

Unsupervised Texture Segmentation[2]: We propose a data-centric approach to efficiently extract and represent textural information for unsupervised texture segmentation problem. Based on the strong self-similarities and quasi-periodicity in texture images, the proposed method first constructs a representative texture [...]

By |August 25th, 2019|News|Comments Off on MCL Research on Texture Analysis & Modeling|

Welcome New MCL Member Jiazhi Li

We are so glad to welcome our new MCL member, Jiazhi Li! Jiazhi is a summer intern in MCL. Here is a short interview with Jiazhi:

1. Could you briefly introduce yourself and your research interests?

My name is Jiazhi Li, a graduate student in Department of Electrical and Engineering of USC. I grew up in Beijing, the capital of China. I received my bachelor’s degree in electrical engineering from Beijing Institute of Technology. During that time, I have worked in Research Group of Medical Information Processing. What’s more, in summer 2017, I have worked in Advanced Integrated Cyber-Physical Systems (AICPS) in University of California, Irvine. After these experiences, I found my interests in computer vision and autonomous driving.

2. What is your impression about MCL and USC?

I have been USC for two semesters, and I’m really impressed by the diversity of USC. The MCL is really a big warm family. The weekly report and weekly meeting push me make progress every week. Also, the pizza party before the seminar encloses the MCL member. What’s more, the seminar is very impressive. One hour per week gives a quick look about research topic of other member, which really extend my interests.

3. What is your future expectation and plan in MCL?

The experiences to do research and learn from other members in MCL is really a treasure for me. I will keep going. Stay hungry for more methods and theories of computer vision and machine learning. What’s more, I will take full advantage of the opportunity to study under the supervision of Prof. Jay Kuo. I believe such experiences will give me a lot in further future.

 

By |August 18th, 2019|News|Comments Off on Welcome New MCL Member Jiazhi Li|

Welcome New MCL Member Wenxuan Li

We are so glad to welcome our new MCL member, Wenxuan Li! Wenxuan is a summer intern in MCL. Here is a short interview with Wenxuan:

1. Could you briefly introduce yourself and your research interests?

My name is Wenxuan Li. I’m a graduate student pursuing master’s degree in Electrical Engineering at USC. I am from a city called Nanjing, which is in the eastern part of China. Prior to coming to USC, I achieved my bachelor’s degree in Electrical Engineering and Automation from Beijing Institute of Technology, 2017. I found my strong interest in machine learning during my curriculum study in EE program. I am also fascinated by image processing problems.

2. What is your impression about MCL and USC?

I was deeply impressed by the beautiful campus when I came to USC for the first time. Students here are full of confidence and passion for learning. USC also offers us great opportunities both in industry and academia. MCL is like a family that strongly connects its members. Everyone here not only focuses on their research topics but also is willing to share and offer help. MCL gives the opportunities to challenge ourselves with frontier research problems

3. What is your future expectation and plan in MCL?

I am working on style transfer topic this summer and hope to learn more about generative model and feature extraction of neural networks. MCL is a great platform to meet people and gain skills. Under insightful guidance from Prof. Kuo and thoughtful advice from PhD mentors, I will quickly expand and improve necessary skills for research.

 

By |August 11th, 2019|News|Comments Off on Welcome New MCL Member Wenxuan Li|

Welcome New MCL Member Shiyu Mou

We are so glad to welcome our new MCL member, Shiyu Mou! Shiyu is a summer intern in MCL. Here is a short interview with Shiyu:

1. Could you briefly introduce yourself and your research interests?

My name is Shiyu Mou, I am a second-year graduate student at USC pursuing a Master’s degree in Electrical and Computer Engineering. I developed a passion for computer vision since undergrad and I started to work on learning-based computer vision projects since grad school, especially 3D computer vision. I’ve been researching on real-world projects for a while now. My previous research experiences include learning-based 3D shape inpainting and 3D human pose estimation from videos.

2. What is your impression about MCL and USC?

MCL is a creative community. Students in the Lab led by Prof. Kuo have the courage to work on something new. They always think things mathematically and logically. During the summer, I am involved in a company project with my mentors and we are trying to overcome some serious real-world challenges. Prof. Kuo is also super supportive and he always brings up creative inspirations for our problems. It’s been a great pleasure to work in MCL.

3. What is your future expectation and plan in MCL?

I am working on a summer project on object classification. Hope I can finish this project with some milestones. I enjoyed my summer internship here and would definitely like to come back MCL in the future.

 

By |August 4th, 2019|News|Comments Off on Welcome New MCL Member Shiyu Mou|

Welcome New MCL Member Muhan Li

We are so glad to welcome our new MCL member, Muhan Li! Here is a short interview with Muhan:
1. Could you briefly introduce yourself and your research interests?

My name is Muhan Li, a graduate student in USC Viterbi School of Engineering. I come from China. My major is Electrical Engineering. Before coming to USC, I received my Bachelor degree from North China Electric Power University. This summer, I join MCL and start a time series project with Prof. Kuo and my mentors (Ruiyuan, Zhiruo and Shuiyang). I’m interested in machine learning and have taken many courses related to this topic. So, it’s glad for me to participate in an interesting project with excellent people in MCL.

2. What is your impression about MCL and USC?

I think MCL is like a big family with many lovely members. Prof. Kuo and my mentors are all enthusiastic and thoughtful person. They provide plenty of helpful suggestions and extra insights to me. When I seek help from other students in MCL, everyone is willing to help, too. I feel so lucky to meet many friends who has same hobby and interests as me in USC. We can do things we both love and gain happiness together.

3. What is your future expectation and plan in MCL?

I hope I can make crucial progress in current research under the supervision of Prof. Kuo and with the help of my mentors. If possible, I want to explore more interesting topics in the field of machine learning and improve myself to be prepared for pursuing PhD.

 

By |July 29th, 2019|News|Comments Off on Welcome New MCL Member Muhan Li|