News

Welcome Jiahao Gu to Join MCL as A Summer Intern

In Summer 2022, we have a new MCL member, Jiahao Gu, joining our big family. Here is a short interview with Jiahao with our great welcome.

Jiahao Gu is currently a master student in Electrical Engineering at USC. He received his bachelor’s degree in Nanjing University of Posts and Telecommunications in 2020.His research interests include point cloud, machine learning and computer vision.

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

My name is Jiahao Gu. I received my bachelor’s degree in Communication Engineering from Nanjing University of Posts and Telecommunications in 2020. I will be a summer intern at MCL. In my spare time, I enjoy reading and traveling. Some of my research interests include machine learning, point cloud and computer vision.

2. What is your impression about MCL and USC?

MCL is a great place to research. People here are friendly, intelligent and hard working. Professor Kuo is responsible to every student including master students like me. Every week, there will be a seminar and people will have lunch together, which is a great chance for us to share ideas and communicate with each other.

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

For this summer, I will work with Pranav on point cloud odometry. I hope I can improve our method and get better performance. I am looking forward to learning a lot under the guidance of Professor Kuo and Pranav. After the summer internship, I hope I can keep working closely with Professor Kuo.

By |July 3rd, 2022|News|Comments Off on Welcome Jiahao Gu to Join MCL as A Summer Intern|

Welcome Hardik Prajapati to Join MCL as A Summer Intern

In Summer 2022, we have a new MCL member, Hardik Prajapati, joining our big family. Here is a short interview with Hardik with our great welcome.

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

Hello, I am Hardik Prajapati. I am currently pursuing my Masters in Electrical and Computer Engineering at USC.I did my undergraduate in Instrumentation and Control Engineering from Nirma University, Ahmedabad(India). I like hiking and doing adventure activities. My research interests lie in the field of Computer vision, Machine Learning and Point Cloud Processing.

2. What is your impression about MCL and USC?

It’s an honor to work at MCL which has been actively functional since 1989. The best thing that I like about MCL is the direction of research that Professor Kuo has been instrumental in setting up. To summarize my impression about MCL I would say “Success meets MCL at a good tradeoff”. USC has a fun vibe going around.

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

I really do not wish to get ahead of myself and rather focus on having a productive and enjoyable summer. I am very hopeful in having rich and interesting conversations, making new friends and getting inspired by Professor Kuo and seniors at the lab.

By |June 26th, 2022|News|Comments Off on Welcome Hardik Prajapati to Join MCL as A Summer Intern|

Congratulations to Yijing Yang for Passing Her Defense

Congratulations to Yijing Yang for passing her defense on June 15, 2022. Her PhD dissertation is titled with “Advanced Techniques for Object Classification: Methodologies and Performance Evaluation”. Her Dissertation Committee members include Jay Kuo (Chair), Justin Haldar, Suya You, and Aiichiro Nakano (Outside Member). All committee members were very pleased with the depth and fundamental nature of Yijing’s research. We are glad to invite Yijing here to share the overview of her thesis study. We wish Yijng all the best for her future career and life!

“Object classification has been studied for many years as a fundamental problem in computer vision. With the development of convolutional neural networks (CNNs) and the availability of larger scale datasets, we see a rapid success in the classification using deep learning. Although being effective, deep learning demands a high computational cost. Another challenge is the amount of accessible labeled data. How the quantity of labeled samples affects the performance of learning systems is an important question in the data-driven era. In this dissertation, we investigate and propose new techniques based on successive subspace learning (SSL) methodology to shed light on the above problems. It can be decomposed into four aspects: 1) improving the performance of SSL-based multi-class classification, 2) improving the performance of resolving confusing sets, 3) enhancing the quality of the learnt feature space by conducting a novel supervised feature selection, and 4) designing supervision-scalable learning systems.

Specifically, in the first two aspects, soft-label smoothing (SLS), hard sample mining, and a new SSL-based attention localization method are proposed to improve the classification performance. In the third part, a novel supervised feature selection methodology is proposed to enhance the learnt feature space, including the discriminant feature test (DFT) and the [...]

By |June 20th, 2022|News|Comments Off on Congratulations to Yijing Yang for Passing Her Defense|
  • Permalink Gallery

    Congratulations to Mozhdeh Rouhsedaghat for Passing Her Defense

Congratulations to Mozhdeh Rouhsedaghat for Passing Her Defense

Congratulations to Mozhdeh for passing her qualifying exam on May 21, 2022. Mozhdeh’s thesis proposal is titled with “Data-Efficient Image and Vision-and-Language Classification and Synthesis”. Her Qualifying Exam committee includes Jay Kuo (Chair), Antonio Ortega, Keith Jenkins, Krishna Nayak and Aiichiro Nakano (Outside Member). Mozhdeh gave an excellent presentation with clarity and highlighted contributions. The Committee was very pleased with Mozhdeh’s high quality research work. We are glad to invite Mozhdeh here sharing the overview of her thesis study. We wish Mozhdeh all the best for her future career and life!

“Image classification and image synthesis are two fundamental yet challenging tasks in computer vision and pattern recognition and have drawn significant research attention over the last several decades. Image classification models learn to predict the probability of an image belonging to different classes. On the other hand, image synthesis models learn the probability distribution of data conditioned on some specific input. With the emergence of Deep Learning (DL) techniques and the availability of large annotated datasets and computational power, classification and generation models could achieve great success, however, in domains with a limited amount of data, leveraging such methods is challenging. Therefore, having data-efficient models requires further attention. In this thesis, we focus on learning-based data-efficient image and vision-and-language classification and image synthesis tasks.

In the first part, initially, we propose a method for data-efficient feature learning from images and video frames and then, use it to propose data-efficient models for face recognition, face gender classification, and also medical vision-and-language classification. We analyze each proposed model carefully and demonstrate their advantages over existing models.

In the second part, we offer a one-shot mask-guided model that allows controlling manipulations of a single image by inverting a quasi-robust [...]

By |June 13th, 2022|News|Comments Off on Congratulations to Mozhdeh Rouhsedaghat for Passing Her Defense|

Welcome Jiaxin Yang to Join MCL as A Summer Intern

In Summer 2022, we have a new MCL member, Jiaxin Yang, joining our big family. Here is a short interview with Jiaxin with our great welcome.

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

My name is Jiaxin Yang. I am a graduate student in USC and major in Electrical Engineering. I joined the MCL lab this summer and my research interests include image processing and machine learning. I hope I can contribute to efficient, robust and weakly supervised learning models, which only need a small amount of labeled data and small model size. These AI models can help people and reduce their workload. For example, some AI models can help doctors to make better decisions about diagnosis and treatment quickly. I think such models and algorithms can change the world one day and bring us a better life.

2. What is your impression about MCL and USC?

MCL lab is an excellent and impressive community. People in the MCL lab unite as a passionate and motivated group and I can feel that everyone is friendly and welcoming. The lab is full of diversity and there are people from all around the world. Professor Jay Kuo is ambitious and wants to contribute himself to the real AI, where I admire his spirit and dream, and in the meantime, he is also kind and intelligent and willing to offer constructive suggestions to everyone.

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

During this summer, I will work with Vasileios Magoulianitis and Yijing Yang on AI for the prostate cancer project, guided by Professor Jay Kuo. I desire to explore machine learning algorithms for the imaging process and their applications in the medical field. And also, I can [...]

By |June 5th, 2022|News|Comments Off on Welcome Jiaxin Yang to Join MCL as A Summer Intern|

Welcome Jintang Xue to Join MCL as A Summer Intern

In Summer 2022, we have a new MCL member, Jintang Xue, joining our big family. Here is a short interview with Jintang with our great welcome.

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

My name is Jintang Xue. I am currently pursuing my Master’s degree in Electrical Engineering at USC. I got my Bachelor’s degree from Shanghai University, majoring in communication engineering. My research interests include machine learning and computer vision. I will work on point cloud classification this summer at MCL. I think it is an excellent opportunity to dive deeper into this field.

2. What is your impression about MCL and USC?

This is my first year at USC. The campus is beautiful. The people here are all very kind. I learned a lot from the valuable courses provided by USC, especially EE 569. MCL is a warm family. People in MCL are friendly, hardworking, and intelligent. They are willing to help each other. I am glad to work with them.

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

I want to make friends and learn from the members of MCL. I find point clouds very interesting. I will work hard on this topic to gain more knowledge and improve my programming skill. I hope I can contribute to MCL. I believe the experience at MCL is valuable in my life.

By |May 29th, 2022|News|Comments Off on Welcome Jintang Xue to Join MCL as A Summer Intern|
  • Permalink Gallery

    Summer 2022 Semester Begins and MCL Resumes on-campus Activities

Summer 2022 Semester Begins and MCL Resumes on-campus Activities

Summer 2022 started on Wednesday, May 18, last week. As Covid-19 is more well-controlled nowadays, we gradually resumed the lab weekly activities on campus. Hope everyone have a great summer time!

 

Image credit:

https://alumni.usc.edu/campus/
https://www.morainevalley.edu/summer22/
https://www.linkedin.com/school/university-of-southern-california-viterbi-school-of-engineering/

By |May 22nd, 2022|News|Comments Off on Summer 2022 Semester Begins and MCL Resumes on-campus Activities|
  • Permalink Gallery

    Congratulations to MCL Members in Attending PhD Hooding Ceremony

Congratulations to MCL Members in Attending PhD Hooding Ceremony

Five MCL members attended the Viterbi PhD hooding ceremony on Wednesday, May 11, 2022, 8:30-11:00 a.m. in the Bovard Auditorium. They were Mozhdeh Rouhsedaghat, Tian Xie, Yijing Yang, Kaitai Zhang, and Min Zhang. Congratulations to them for their accomplishments in completing their PhD program at USC!

Mozhdeh Rouhsedaghat received her Bachelor’s in Electrical Engineering from the Sharif University of Technology in 2017 and then joined the University of Southern Californian for her Ph.D. studies in Fall 2017. She received her Master’s and Ph.D. in Electrical Engineering from the University of Southern California in 2021 and 2022, respectively. Her research interests include computer vision, vision-and-language, and adversarial learning. Her Ph.D. thesis title is “Data-Efficient Image and Vision-and-Language Synthesis and Classification”.

Tian Xie received his B.S. degree in Physics from Fudan University, Shanghai, China, in 2017. He then joined the University of Southern California (USC) as a Ph.D. student. His research interest is graph learning, machine learning, and data mining. His thesis title is “Efficient Graph Learning: Theory and Performance Evaluation”. He will join Meta as a Research Scientist.

Yijing Yang received her Bachelor’s degree in 2016 from Tianjin University, China, and received her Master’s degree in Electrical Engineering from USC in 2018. She then joined MCL as a PhD student guided by Prof. C.-C. Jay Kuo. Her research interests include image processing, computer vision, and medical image analysis.

Kaitai Zhang defended his Ph.D. in Electrical and Computer Engineering and graduated from University of Southern California in May 2021, where he is fortunate enough to be advised by Professor C.-C. Jay Kuo. During his PhD study, Kaitai conducted research projects from image processing to computer vision using various machine learning and deep learning techniques. Before that, he obtained his bachelor’s [...]

By |May 16th, 2022|News|Comments Off on Congratulations to MCL Members in Attending PhD Hooding Ceremony|

Congratulations to Tian Xie for Passing His Defense

Congratulations to Tian Xie for passing his defense on May 4, 2022! His Ph.D. thesis is entitled “Efficient Graph Learning: Theory and Performance Evaluation”. Here we invite Tian to share a brief introduction of his thesis and some words he would like to share at the end of the Ph.D. study journey.

1) Abstract of Thesis

Graphs are generic data representation forms that effectively describe the geometric structures of data domains in various applications. Graph learning, which learns knowledge from this graph-structured data, is an important machine learning application on graphs. In this dissertation, we focus on developing efficient solutions to graph learning problems. In particular, we first present an advanced graph neural network (GNN) method specified for bipartite graphs that is scalable and without label supervision. Then, we investigate and propose new graph learning techniques from the aspects of graph signal processing and regularization frameworks, which identify a new path in solving graph learning problems with efficient and effective co-design.

From the GNN perspective, we extend the general GNN to the node representation learning problem in bipartite graphs. We propose a layerwise-trained bipartite graph neural network (L-BGNN) to address the challenges in bipartite graphs. Specifically, L-BGNN adopts a unique message passing with adversarial training between the embedding space. In addition, a layerwise training mechanism is proposed for efficiency on large-scale graphs.

From the graph signal perspective, we propose a novel two-stage training algorithm named GraphHop for the semi-supervised node classification task. Specifically, two distinctive low-pass filters are respectively designed for attribute and label signals and combined with regression classifiers. The two-stage training framework enables GraphHop scalable to large-scale graphs, and the effective low-pass filtering produces superior performance in extremely small label rates.

From the regularization framework perspective, we [...]

By |May 9th, 2022|News|Comments Off on Congratulations to Tian Xie for Passing His Defense|

MCL Research on Facial Emotion Classification

Facial Expression Recognition (FER) is a challenging topic in the image classification field. Some of its applications, such as driver assistance systems, require real-time response or demand methods that can run on low-resources devices. FER can be classified into conventional methods and deep learning methods. Deep learning-based methods have attracted much attention in recent years because of their higher performance even under challenging scenarios. However, deep learning-based methods rely on models that demand high computational resources. At the same time, conventional methods depend on hand-crafted features that may not perform well in different scenarios. In this context, some studies are pursuing to reduce the computational complexity of deep learning models while achieving similar results to those more complex models. But even these models with reduced complexity can require a lot of computational resources.

To tackle this problem, we propose ExpressionHop. ExpressionHop is based on a Successive Subspace Learning classification technique called PixelHop[1], which allows us to automatically extract meaningful features without the need for higher computational demanding models. As shown in Figure1, we first extract facial landmark patches from face images, and then use Pixelhop to extract feature. Discriminant feature test is utilized for feature selection before doing classification using logistic regression. As shown in table1, our model achieved higher or similar results compared to traditional and deep learning methods for JAFFE, CK+, and KDEF datasets. At the same time, a comparison of the number of parameters of the models indicates that the proposed model demands fewer computational resources even when compared to newer deep learning methods that rely on reduced complexity models.

 

— By Chengwei Wei and Rafael Luiz Testa

By |May 1st, 2022|News|Comments Off on MCL Research on Facial Emotion Classification|