ZhiruoZhou

Could you briefly introduce yourself and your research interests?

My name is Ganning Zhao. I was born in Weifang, China. This is my first semester here in USC, pursuing master’s degree on Electrical Engineering. I graduated from Guangdong University of Technology, majoring in automation. In my undergraduate, I did a project about audio signal processing using convolutional neural network with my friends and I became interested in signal processing and machine learning since then. My current research interest is image processing and computer vision.

What is your impression about MCL and USC?

I like the campus of USC, because the buildings are beautiful. Particularly, there are many libraries in USC and many of them are exquisite. People in MCL are intelligent and work very hard. I’m also impressed that they are very nice and always willing to help with each other. Professor Kuo is also very nice and caring about everyone in lab. I like the atmosphere here in MCL.

What is your future expectation and plan in MCL?

My research topic in this summer is texture synthesis. I hope I can do a good job in this topic. More importantly, because everyone in MCL are intelligent, I hope I can learn a lot from them during communication and improve my research ability. Also, I want to make more friends here in MCL.

Could you briefly introduce yourself and your research interests?

My name is Zheng Wen, I’m currently pursuing my Master’s degree at USC in Electrical Engineering. I received my Bachelor’s degree in Beihang University, Beijing, China. I’m very curious in math and programming. I found it interesting to do something related matrix and machine learning, so I’m very glad that I Professor Kuo could give me this opportunity to join MCL and dive deeper in image processing, computer vision and machine learning.

What is your impression about MCL and USC?

This is my first year in USC, I found the campus is very beautiful even though kind of small. Leavey Library is a good place to study when we are struggling for the final exams of a semester. I really enjoy the American Chinese cuisine offered by the canteen. MCL is a big family. I get to know the members in MCL by EE569, Professor Kuo is an expert in multimedia, and his understanding in deep learning impressed me a lot. TAs are very experience in image processing and willing to help us.

What is your future expectation and plan in MCL?

In MCL, I want to do some project in image forensics with the help of Yao, learn more about image processing and machine learning, also sharpen my programming skills and make some progress to the domain. I will try my best to get involved in MCL and make friends with everyone.

Let us hear what she wants to say about her defense and an abstract of her thesis.

Deep learning techniques utilize networks with multiple layers cascaded to map the inputs to desired outputs. To map the entire inputs to desired outputs, useful information should be extracted through the layers. During the mapping, feature extraction and prediction are jointly performed. We do not have direct control for feature extraction. Consequently, some useful information, especially local information, is also discarded in the process.

In this thesis, we specifically study local-aware deep learning techniques from four different aspects: 1) Local-aware network architecture 2) Local-aware proposal generation 3) Local-aware region analysis 4) Local-aware supervision

Specifically, we design a multi-modal attention mechanism for generative visual dialogue system, which simultaneously attends to multi-modal inputs and utilizes extracted local information to generate dialogue responses. We propose a proposal network for fast face detection system for mobile devices, which detects salient facial parts and uses them as local cues for detection of entire faces. We extract representative fashion features by analyzing local regions, which contain local fashion details of humans’ interests. We develop a fashion outfit compatibility learning method, which models each outfit as a graph and learns outfit compatibility using both global and local supervisions on the graphs.

I would like to thank Prof. Kuo and all the lab members for their help. I have learned a lot through my PhD journey and I want to share some feelings and experiences. One essential part of the doctoral training is mental training, from which I have become more persistent, self-disciplined and motivated. As this journey may take several years, maintaining a balanced life is very important. I wish the best to all the lab members and [...]

In the task of fashion compatibility prediction, the goal is to pick an item from a candidate list to complement a partial outfit in the most appealing manner. Existing fashion compatibility recommendation work comprehends clothing images in a single metric space and lacks detailed understanding of users’ preferences in different contexts. To address this problem, we propose a novel Metric-Aware Explainable Graph Network (MAEG). In MAEG, we leverage a Latent Semantic Extraction Network (LSEN) to obtain representations of items in the metric-aware latent semantic space. Then, we develop a graph filtering network and Pairwise Preference Attention (PPA) module to model the interactions between users’ preferences and contextual information. With MAEG, we can provide recommendation to users as well as explain how each item and factor contribute to the final prediction. Extensive experiments on two large-scale real-world datasets reveal that MAEG not only outperforms the state-of-the-art methods, but also provides interpretable insights by highlighting the role of semantic attributes and contextual relationships among items.

MCL Director, Professor Kuo, gave an invited speech at Kyoto University on December 19, 2019. The title of his speech was “From Feedforward-Designed Convolutional Neural Networks (FF-CNNs) to Successive Subspace Learning (SSL)”.  Professor Kuo’s visit to Kyoto University was hosted by Professor Tatsuya Kawahara. The lecture was also an event of IEEE SPS Kansai Chapter.

The abstract of his speech is given below. “Given a convolutional neural network (CNN) architecture, its network parameters are typically determined by backpropagation (BP). The underlying mechanism remains to be a black-box after a large amount of theoretical investigation. In this talk, I will first describe a new interpretable feedforward (FF) design with the LeNet-5 as an example. The FF-designed CNN is a data-centric approach that derives network parameters based on training data statistics layer by layer in a one-pass feedforward manner. To build the convolutional layers, we develop a new signal transform, called the Saab (Subspace approximation with adjusted bias) transform. The bias in filter weights is chosen to annihilate nonlinearity of the activation function. To build the fully-connected (FC) layers, we adopt a label-guided linear least squared regression (LSR) method. To generalize the FF design idea furthermore, we present the notion of “successive subspace learning (SSL)” and present a couple of concrete methods for image and point cloud classification. Experimental results are given to demonstrate the competitive performance of the SSL-based systems. Similarities and differences between SSL and deep learning (DL) are compared.”