News

We are so happy to welcome a new graduate member, Gagan Ellath, joining MCL this summer. Here is a quick interview with Gagan:

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

My name is Gagan. I am a 2nd-year Graduate student pursuing my Master’s Degree in Computer Engineering. My research interests include Image Processing, Machine Learning, Computer Networks, and Operating Systems.

I am also interested in learning the underlying implementation of complex machine learning algorithms such as GANs and Transformer models and why they work well.

2. What is your impression about MCL and USC?

Doing my Master’s Degree at USC is a great experience. There are people from different regions and cultures who you interact with and help you see different perspectives.

As for MCL, Professor Kuo and all the students currently working in MCL are very smart, the weekly seminars showcase how much work goes into each research topic, and it also helps me

think about different solutions for my research problem.

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

I want to publish a research paper on adversarial attacks in the green learning pipeline, and in the process, I would like to understand the robustness of the green learning model.

I would also like to interact and get to know everyone from the Lab and learn as much as possible from them.

We are so happy to welcome the summer intern of MCL, Tiankai Yang. Here is an interview with Tiankai:

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

I am Tiankai Yang, a second-year graduate student at USC. My research journey began five years ago. During undergraduate study, I focused on AI operation (AIOps). After one and a half years of hard work, I became a main member of the project in my fourth year. Despite the challenges, I found machine learning and deep learning fascinating then as well as now. However, I soon realized that my basic knowledge was insufficient, which led me to choose Machine Learning and Data Science as my major for graduate study. Currently, I am interested in exploring both practical and theoretical topics related to machine learning.

2. What is your impression about MCL and USC?

At USC, I met great professors and learned from the well-designed graduate courses . It helps me build a strong foundation in machine learning. The MCL group is outstanding and motivated. Professor Kuo and senior students set excellent role models for me with their passion for achieving research goals. Also, the MCL community feels like a big family where people share interesting experiences and learn from each other. It is my pleasure to be part of this group.

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

I expect to achieve good results on my edge detection project this summer. If possible, I would like to learn about generative AI in green learning, and explore interpretable and reliable machine learning solutions for real scenarios. I also look forward to building lasting relationships with the talented individuals in the lab.

Congratulations to Yao Zhu for passing her defense on June 12, 2023. Yao’s thesis is titled “A Green Learning Approach to Image Forensics: Methodology, Applications, and Performance Evaluation.” Her Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Jernej Barbic (Outside Member). Yao received several questions and suggestions from the Committee members. Yao answered the questions professionally.

Congratulations to Yao for this milestone moment in life. MCL News team invited Yao for a short talk on her thesis and PhD experience, and here is the summary. We thank Yao for her kind sharing, and wish her all the best in the next journey.

“Fake images have become a central problem in the last few years, especially after the advent of neural networks. Fake images are usually created by whole generation, partial tampering or information hiding. Image forensics, on the contrary, aims to detect the fake contents or discover the hidden information from fake objects. It leverages the fact that manipulation actions leave detectable traces, making fake images statistically distinguishable from genuine ones.

I specifically talked about two long-standing problems in image forensics: GAN- generated image detection and spatial image steganalysis. The former one aims to detect images that are synthesized by generative models. The latter one focus on distinguishing stego and cover images in spatial domain, where stego images are generated by various content-adaptive steganography algorithms. The stego signal that are embedded into cover images is so weak that the difference in pixel domain in only +1 or -1. The solutions that we propose to these two problems are both ‘green’ solutions, which have significantly small model sizes and computational cost. In the meantime, our methods are mathematically transparent due to the modularized design. Green [...]

Camouflage is an attempt to mask the object into a background image and to match its background. The term “camouflage” originates in the ancient practices of the animal kingdom, where animals would alter their body patterns, textures, and colors to blend in with their environment to evade predators. In military contexts, camouflage is a technique used to conceal soldiers or equipment within the background texture, making it difficult for the enemy to detect them. On the other hand, camouflaged object detection is a method used to uncover the enemy who has used camouflage to hide within the image texture.

Our research objectives are to understand the problem with more insights and develop a pipeline for Camouflaged Object Detection based on the Green Learning framework. The first main technical accomplishments are multiscale color and texture decomposition; since, in this task, the texture is much more important than the color, we decouple the information of textures and colors. The second main technical accomplishment is clustering the images dataset; we cluster similar photos with the matching color histogram together and try to learn the information. It reduces the difficulty of the classifier to separate all kinds of images, and we can focus more on images with similar colors and appearance. We cluster the dataset using HSV color space, quantize the color space into 52 bins, and use K-means clustering to derive the clusters. As shown in Figure, images with similar backgrounds are grouped together. Our experiment shows that training in each subcluster could further reduce training and validation loss.

— Max Chen

Martin Ohm (May 6, 1792 in Erlangen – April 1, 1872 in Berlin) was a German mathematician and a younger brother of physicist Georg Ohm. He earned his doctorate in 1811 at Friedrich-Alexander-University, Erlangen-Nuremberg where his advisor was Karl Christian von Langsdorf. In 1817, he was appointed professor of mathematics and physics in the gymnasium at Thorn. In 1821 he moved to Berlin, and in 1839 became a full professor in the University of Berlin. He delivered courses of lectures at the academy of architecture from 1824 to 1831, and at the schools of artillery and engineering from 1833 to 1852; and he also taught in the military school from 1826 to 1849. Ohm was the first to fully develop the theory of the exponential ab when both a and b are complex numbers in 1823. The 1835 second edition of Ohm’s textbook, Die reine Elementar Mathematik was the first time that Euclid’s ‘extreme and mean ratio’ was given the name of the “golden section” (goldener Schnitt). Ohm’s notable students included Rudolf Lipschitz.

— Xiou Ge

Source: https://en.wikipedia.org/wiki/Martin_Ohm