News

Let us hear what he has to say about his defense and an abstract of his thesis.

Deep learning has brought impressive improvements in many fields, thanks to end-to-end data-driven optimization. However, people have little control over the system during training and limited understanding about the structure of knowledge being learned. In this thesis, we study theory and applications of adversarial and structured knowledge learning: 1) learning adversarial knowledge with human interaction or by incorporating human-in-the-loop; 2) learning structured knowledge by modelling contexts and users’ preferences via distance metric learning.

In the first part, we teach a robotic arm to learn robust manipulation grasps that can withstand perturbations, through end-to-end optimization with a human adversary. Specifically, we formulate the problem as a two-player game with incomplete information, played by a human and a robot, where the human’s goal is to minimize the reward the robot can get. We then extend this idea to improve the sample efficiency of deep reinforcement learning by incorporating human in the training loop. We presented a portable, interactive and parallel platform for human-agent curriculum learning experience.

In the second part, we present two works that address different aspects of structured representation learning. First, we proposed a self-training framework to improve distance metric learning. The challenge is the noise in pseudo labels, which prevents exploiting additional unlabeled data. Therefore, we introduced a new feature basis learning component for the teacher-student network, which better measures pairwise similarity and selects high confidence pairs. Second, we address image-attribute query, which allows a user to customize image-to-image retrieval by designating desired attributes in target images. We achieve this by adopting a composition module, which enforces object-attribute factorization and an attribute-set synthesis module to deal with sample insufficiency.

Looking back, Prof. Kuo is [...]

Object tracking is a fundamental computer vision problem that finds a wide range of applications, such as video surveillance, smart traffic system, autonomous driving cars and so on. Nowadays, most state-of-the-art object trackers adopt deep neural networks for high tracking performance at the expense of huge computational resources and heavy memory use. Here, we seek a more lightweight solution that requires fewer resources for training and inference and has a much smaller model size, thus making real-time tracking possible on small devices such as mobile phone and autonomous drones.

The proposed object tracker is built upon the PixelHop framework so that it is called OTHop (Object Tracking PixelHop). The term “hop” denotes the neighborhood of a pixel. OTHop conducts spectral analysis using Saab transform on neighborhoods of various sizes centered on a pixel through a sequence of cascaded dimension reduction units, which naturally forms a multi-resolution feature extraction scheme, thus helping capture unusual patterns that we should pay more attention to during tracking. Then we adopt the XGBoost classifier as the binary predictor to differentiate foreground pixels and background pixels. The classifier is pre-trained on some offline dataset and then updated online using either the initial frame or preceding frames with Saab coefficients as the input. Base on the classification results we derive the object bounding box.

To sum up, OTHop has the following main steps:

Extract joint spatial-spectral features based on the PixelHop framework;
Predict the probability of a spatial region, which can be of various sizes, of being a foreground object or a background region with a trained XGBoost binary classifier;
Fuse results obtained at different hops in Steps 2 to obtain the ultimate object bounding boxes.

The tracker is tested on the [...]

As the number of Deepfake video contents grows rapidly, automatic Deepfake detection has received a lot of attention in the community of digital forensics. Deepfake videos can be potentially harmful to society, from non-consensual explicit content creation to forged media by foreign adversaries used in disinformation campaigns.

A light-weight high-performance Deepfake detection method, called DefakeHop, is proposed in this work. State-of-the-art Deepfake detection methods are built upon deep neural networks. DefakeHop extracts features automatically using the successive subspace learning (SSL) principle from various parts of face images. DefakeHop consists of three main modules: 1) PixelHop++, 2) feature distillation and 3) ensemble classification. To derive the rich feature representation of faces, DefakeHop extracts features using PixelHop++ units from various parts of face images. The theory of PixelHop++ have been developed by Kuo et al. using SSL. PixelHop++ has been recently used for feature learning from low-resolution face images but, to the best of our knowledge, this is the first time that it is used for feature learning from patches extracted from high-resolution color face images. Since features extracted by PixelHop++ are still not concise enough for classification, we also propose an effective feature distillation module to further reduce the feature dimension and derive a more concise description of the face. Our feature distillation module uses spatial dimension reduction to remove spatial correlation in a face and a soft classifier to include semantic meaning for each channel. Using this module the feature dimension is significantly reduced and only the most important information is kept. With a small model size of 42,845 parameters, DefakeHop achieves state-of-the-art performance with the area under the ROC curve (AUC) of 100%, 94.95%, and 90.56% on UADFV, Celeb-DF v1 and Celeb-DF v2 datasets, [...]

We have a new member, Jiahui Zhang, joining MCL in Spring 2021. Here is a short interview with Jiazhi with our great welcome.

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

My name is Jiahui Zhang, I am a second-year master student in the Department of Electronic Engineering in USC. I got my bachelor degree from Beijing University of Technology. I am a sports fan. In my spare time, I like playing sports and watching sports games. I also like traveling to view good scenery. My research interests include deep learning, computer vision especially representation learning.

2. What is your impression about MCL and USC?

USC is a great school that could provide student a enjoyable environment on living, communicating and studying.

MCL is a wonderful lab filled with a number of intelligent researchers. Everyone is an expert in their research field. Besides, people in MCL lab from Professor Kuo to every lab member are very kind and friendly. People help each other on living, studying, and researching, which build a warm environment in the lab.

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

MCL has many great and excellent researchers, and I want to study and make friends with them. For academic, I want to accomplish some projects to accumulate my research experiences and make contribution to the lab.

Research related to the future development of Health Care systems is always a significant endeavor, by touching many people lives. AI advancements in the last decade have given rise to new applications, with key aim to increase the automation level of different tasks, currently being carried out by experts. In particular, medical image analysis is a fast-growing area, having also been revolutionized by modern AI algorithms for visual content understanding. Magnetic Resonance Imaging (MRI) is widely used by radiologists in order to shed more light on patient’s health situation. It can provide useful cues to experts, thus assisting to take decisions about the appropriate treatment plan, maintaining also less discomfort for the patient and incurring less economical risks in the treatment process.

The question arises, how modern AI could contribute to automate the diagnosis process and provide a second and more objective assessment opinion to the experts. Many research ideas from the visual understanding area, adopt the deep learning (DL) paradigm, by training Deep Neural Networks (DNNs) to learn end-to-end representations for tumor classification, lesion areas detection, specific organ segmentation, survival prediction etc. Yet, one could identify some limitations on using DNNs in medical image analysis. It is well known that it is often hard to collect sufficient real samples for training DL models. Furthermore, decisions made by machines need to be transparent to physicians and especially be aware of the factors that led to those decisions, so that they are more trustworthy. DNNs are often perceived as “black-box” models, since their feature representations and decision paths are hard to be interpreted.

In MCL, we consider a new line of research on AI for medical image analysis, by adopting the Green Learning (GL) approach to address [...]