weiwang

  • Permalink Gallery

    MCL Received Sponsored Research from Army Research Laboratory

MCL Received Sponsored Research from Army Research Laboratory

MCL received a grant from the US Army Research Laboratory (ARL) recently for joint research on theory and applications of artificial intelligence (AI) and machine learning (ML) technologies. Through this support, MCL researchers will collaborate with ARL researchers to conduct fundamental and applied research in the next 4 years.

The fundamental research targets at explainable neural networks. Cybenko and Hornik et al. proved that the multi-layer perceptron (MLP) is a universal approximator in late 80s, which appears to be the most important theoretic result even up to now. However, for a given dataset, they do not provide a constructive procedure to build the MLP. We will investigate a systematic way to specify an MLP architecture and determine its model parameters. Resource-rich and resource-scarce networks refer to those have abundant and fewer model parameters, respectively. The objective of the stress test study is to understand the behavior of the transition of a network from a resource-rich one to a resource-scarce one. We would like to understand the behavior transition in several areas, including model sensitivity to different weight initializations, classification accuracy, overfitting, etc.

The applied research targets at spatial-temporal attention and semantic scene understanding via successive subspace learning (SSL). To extract key spatial-temporal information from visual data, facilitates video processing and understanding down-stream tasks. For example, an image contains one or several objects. Object detection and recognition is critical to image understanding. Also, motion provides cues for object tracking in video understanding. The sponsored research will also focus on two issues on multi-modality data, say, those obtained by RGB, depth and infrared sensors: 1) representation of multi-domain data and 2) understanding of multi-domain data.

 

—- by Dr. C.-C. Jay Kuo

By |August 2nd, 2020|News|Comments Off on MCL Received Sponsored Research from Army Research Laboratory|

MCL Research on Image Super-resolution

Image super-resolution (SR) is a classic problem in computer vision (CV), which aims at recovering a high-resolution image from a low-resolution image. As a type of supervised generative problem, image SR attracts wide attention due to its strong connection with other CV topics, such as object recognition, object alignment, texture synthesis and so on. Besides, it has extensive applications in real world, for example, medical diagnosis, remote sensing, biometric information identification, etc.

For the state-of-the-art approaches for SR, typically there are two mainstreams: 1) example-based learning methods, and 2) Deep Learning (CNN-based) methods. Example-based methods either exploit external low-high resolution exemplar pairs [1], or learn internal similarity of the same image with different resolution scales [2]. In order to tackle model overfitting and generativity, some dictionary strategies are normally applied for encoding (e.g. Sparse coding, SC). However, features used in example-based methods are usually traditional gradient-related or just handcraft, which may affect model efficiency. While CNN-based SR methods (e.g. SRCNN [3]) does not really distinguish between feature extraction and decision making. Lots of basic CNN models/blocks are applied to SR problem, e.g. GAN, residual learning, attention network, and provide superior SR results. Nevertheless, the non-explainable process and exhaustive training cost are serious drawbacks of CNN-based methods.

By taking advantage of reasonable feature extraction [4], we utilize spatial-spectral compatible features to express exemplar pairs. In addition, we formulate a Successive-Subspace-Learning-based (SSL-based) method to partition data into subspaces by feature statistics, and apply regression in each subspace for better local approximation. Moreover, some adaptation is also manipulated for better data fitting. In the future, we aim at providing such a SSL-based explainable method with high efficiency for SR problem.

— By Wei Wang

 

Reference:

[1] Timofte, Radu, Vincent De Smet, and [...]

By |April 6th, 2020|Computer Vision and Scene Analysis, News, Research|Comments Off on MCL Research on Image Super-resolution|

MCL Research on Statistics-based Attention

Object detection and recognition has always been one of the key challenges in the field of computer vision for finding and identifying objects in an image or video sequence. Humans recognize a multitude of objects in images with little effort, despite the fact that the image of the objects may vary somewhat in different view points, in many different sizes and scales or even when they are translated or rotated. Many approaches to the task have been implemented over multiple decades, including handcrafted features, machine learning algorithms and deep learning.

Recently breakthrough results have been made via Deep Learning with loads of labelled data for supervised training, while Deep Learning is notorious for lacking in scalability and interpretability. With the advantage of recent proposed scalable and interpretable Pixelhop model [1] and pixelhop++ [2], a new object detection pipeline can be proposed via Object Proposal-> Feature Extraction using SSL ->  Classification, thus a machine learning based Statistic-based attention is the key to generate object proposals.

Apart from Deep Learning, object proposal via visual saliency on single images such as DRFI [3] can be a good start for a machine learning based object proposal. To further take advantage of the statistics from training data, we formulate the weakly supervised object proposal problem into object search with features capable of matching, such as SURF [4]. In the future, we aim to improve these results by further exploration with a query-retrieval based saliency proposal method along with adapted bag of word features.

 

-By Hongyu Fu

[1] Yueru Chen and C-C Jay Kuo, “Pixelhop: A successive subspace learning (ssl) method for object recognition,” Journal of Visual Communication and Image Representation, p. 102749, 2020.

[2]Yueru Chen , Mozhdeh Rouhsedaghat , Suya You, Raghuveer Rao and C.-C. Jay Kuo, [...]

By |March 22nd, 2020|News, Research|Comments Off on MCL Research on Statistics-based Attention|

MCL Research on SSL-based Graph Learning

In this research, we proposed an effective and explainable graph vertex classification method, called GraphHop. Unlike the graph convolutional network (GCN) that is based on the end-to-end optimization, the GraphHop method generates an effective feature set for each vertex in an unsupervised and feedforward manner. GraphHop determines the local-to-global attributes of each vertex through successive one-hop information exchange, called the GraphHop unit. The GraphHop method is mathematically transparent. It can be explained using the recently developed “successive subspace learning (SSL)” framework [1, 2], which is mathematically transparent. Unlike GCN that is based on the end-to-end optimization of an objective function using back propagation, GraphHop generates an effective feature set for each vertex in an unsupervised and feedforward manner. Since no backpropagation is required in the feature learning process, the training complexity of GraphHop is significantly lower. By following the traditional pattern recognition paradigm, the GraphHop method decouples the feature extraction task and the classification task into two separate modules, where the feature extraction module is completely un-supervised. In the feature extraction module, GraphHop determines the local-to-global attributes of each vertex through successive one-hop information exchange, called the GraphHop unit. To control the rapid increase of the dimension of vertex attributes, the Saab transform is adopted for dimension reduction inside the GraphHop unit. Multiple Graph-Hop units are cascaded to obtain the higher order proximity information of a vertex. In the classification module, vertex attributes of multiple GraphHop units are extracted and ensembled for the classification task. There are many machine learning tools to be considered. In the experiments, we choose the random forest classifier because of its good performance and low complexity. To demonstrate the effectiveness of the GraphHop method, we apply it to three real-world [...]

By |March 17th, 2020|News, Research|Comments Off on MCL Research on SSL-based Graph Learning|

MCL Research Presented at WACV 2020

MCL member, Junting Zhang presented her paper at 2020 Winter Conference on Applications of Computer Vision (WACV ’20), in Snowmass village, Colorado. The title of Junting’s paper is “Class-incremental Learning via Deep Model Consolidation”, with Jie Zhang, Shalini Ghosh, Dawei Li, Serafettin Tasci, Larry Heck, Heming Zhang, C.-C. Jay Kuo as co-authors. Here is a brief summary of Junting’s paper:

“Deep neural networks (DNNs) often suffer from “catastrophic forgetting” during incremental learning (IL) — an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of classes. Existing IL approaches tend to produce a model that is biased towards either the old classes or new classes, unless with the help of exemplars of the old data. To address this issue, we propose a class-incremental learning paradigm called Deep Model Consolidation (DMC), which works well even when the original training data is not available. The idea is to first train a separate model only for the new classes, and then combine the two individual models trained on data of two distinct set of classes (old classes and new classes) via a novel double distillation training objective. The two existing models are consolidated by exploiting publicly available unlabeled auxiliary data. This overcomes the potential difficulties due to the unavailability of original training data. Compared to the state-of-the-art techniques, DMC demonstrates significantly better performance in image classification (CIFAR-100 and CUB-200) and object detection (PASCAL VOC 2007) in the single-headed IL setting.”

Junting was also invited to attend the WACV 2020 Doctoral Consortium (WACVDC) to present her research and progress to date. She also shared this experience with us:

“It was a great opportunity to interact with experienced researchers in [...]

By |March 8th, 2020|News|Comments Off on MCL Research Presented at WACV 2020|

Welcome Professor Junsong Yuan’s Visit to USC/MCL

Prof. Junsong Yuan visited USC/MCL on Feb. 25, and delivered a talk on “Beyond Deep Recognition: Discovering Visual Patterns in Big Visual Data ”. Thanks to the success of deep learning, many computer vision tasks nowadays are formulated as regression problems, which, however, often relies on large amounts of annotated training data to make the high-dimensional regression successful. In this talk, Prof. Yuan discussed a complementary yet overlooked problem beyond deep visual recognition and regression. He addressed why and how to discover visual patterns in images and videos that are not annotated, e.g., unsupervised and weakly-supervised visual learning and pattern discovery, and explore how to utilize them to better model, search, and interpret big visual data. Applications in visual search, object detection, action recognition, and video analytics were also explored. 

Junsong Yuan is an Associate Professor and Director of Visual Computing Lab of CSE Department, State University of New York at Buffalo. Before that he was an Associate Professor at Nanyang Technological University (NTU), Singapore. He received his PhD from Northwestern University and M.Eng. from National University of Singapore. He is currently Associate Editor of IEEE Trans. on Image Processing (T-IP) and Machine Vision and Applications (MVA), and Senior Area Editor of Journal of Visual Communication and Image Representation (JVCI), and served as program co-chair for ICME 2018 and area chair for CVPR/ACM MM/WACV/ACCV/ICIP/ICPR etc. He received Best Paper Award from IEEE Trans. on Multimedia, Nanyang Assistant Professorship from NTU, and Outstanding EECS Ph.D. Thesis award from Northwestern University. He is a Fellow of International Association of Pattern Recognition (IAPR).

By |March 2nd, 2020|News|Comments Off on Welcome Professor Junsong Yuan’s Visit to USC/MCL|

Welcome New MCL Member Hamza Ghani

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

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

My name is Hamza Ghani and I am from Austin, Texas. I am a graduate student here at USC pursuing a Masters in Electrical Engineering. I went to UT Austin for my undergrad which was in ECE focusing on computer engineering. I also currently work full-time as a Data Scientist while pursuing my Masters. My research interests include: Machine Learning, Graphs and GANs.

2. What is your impression about MCL and USC?

All the members I’ve met in MCL are very knowledgeable in several topics. I am definitely learning a lot by interacting with everyone.  Additionally, everyone I’ve worked with in MCL has been great/enjoyable to work with. I want to thank Professor Kuo for giving me a chance to join the MCL lab and I don’t think my USC experience would be the same without MCL. USC has been great so far, the campus is really nice and it’s easy to make friends even outside of my major.

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

My current goal is to successfully complete the project my team is currently working on regarding model compression. Overall I want to keep learning through research work, publish papers and make connections with my peers in the lab. 

By |February 25th, 2020|News|Comments Off on Welcome New MCL Member Hamza Ghani|

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|