News

We are so happy to welcome a new graduate member of MCL, Hongyu Fu. Here is an interview with Hongyu:

1. Could you briefly introduce yourself and your research interests?
My name is Hongyu Fu, before becoming a PhD student in USC, I got my bachelor’s degree in electrical engineering from Peking University. My past research experience focuses mostly on semiconductor device physics and circuits, while exploring device and circuit based neuromorphic computing and machine learning topics, I have heard more and more about computer vision, AI and machine learning, which are always my keen interest that I haven’t got chances to learn before. Therefore, I really appreciate Prof. Kuo for giving me this opportunity to study in MCL and explore more in this exciting area.
 
2. What is your impression about MCL and USC?
I really love the beautiful campus, friendly atmosphere and enjoy the convenient facilities of USC. We have a fight-on spirit as Trojans, which makes USC a great network and everyone in this network passionate and motivated. MCL is a large and efficient group with a hard-working spirit and intelligent students with solid skills and deep knowledge under the supervision of Prof. Kuo, who is a very nice and responsible advisor profound in knowledge and research.
 

3. What is your future expectation and plan in MCL?
I will definitely work hard, learn solid skills of math, problems solving and research and hope to contribute to MCL in the future. I wish that in the near future, the MCL group and myself would have a solid standing in the machine learning and computer vision community and contribute to the improvement of this field.

The thesis is entitled “Object Classification Based on Neural-Network-Inspired Image Transforms”.

Abstract of the thesis:

Convolutional neural networks (CNNs) have recently demonstrated impressive performance in image classification and change the way building feature extractors from carefully handcrafted design to automatically deep learned from a large labeled dataset. However, a great majority of current CNN literature are application-oriented, and there is no clear understanding and theoretical foundation to explain the outstanding performance and indicate the way to improve. In this thesis, we focus on solving the image classification problem-based on the neural-network-inspired transforms.

Being motivated by the multilayer RECOS (REctified-COrrelations on a Sphere) transform, two data-driven signal transforms are proposed, called the “Subspace approximation with augmented kernels” (Saak) transform and “Subspace approximation with adjusted bias” (Saab) transform corresponding to each Convolutional layers in CNNs. Based on the Saak transform, We firstly proposed an efficient, scalable and robust approach to the handwritten digits recognition problem. Next, we also develop an ensemble method using Saab transform to solve the image classification problem. The ensemble method fuses the output decision vectors of Saab-transform-based decision system. To enhance the performance of the ensemble system, it is critical to increasing the diversity of FF-CNN models. To achieve this objective, we introduce diversities by adopting three strategies: 1) different parameter settings in convolutional layers, 2) flexible feature subsets fed into the Fully-connected (FC) layers, and 3) multiple image embeddings of the same input source.  We also extend our ensemble method to semi-supervised learning. Since unlabeled data may not always enhance semi-supervised learning, we define an effective quality score and use it to select a subset of unlabeled data in the training process. In the last, we proposed a unified framework, called successive subspace learning [...]

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 [...]

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.

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.