Mahtab_Movahhedrad

MCL Research on SLMBoost Classifier

In a Machine Learning framework, there are three fundamental components that play a crucial role: feature extraction, feature selection, and decision model. In the context of Green Learning, we have Saab transform and Least-squares Normal Transform for feature extraction. Regarding feature selection, we have the Discriminant Feature Test (DFT) and Relevant Feature Test (RFT). However, we do not have a green and interpretable solution for the decision model. For a long time, we applied gradient-boosted trees such as XGBoost or LightGBM as the classifier. Yet, it is known that XGBoost or LightGBM models sacrifice interpretability for performance. Also, the large model size of XGBoost or LightGBM is becoming a huge burden for Green Learning. Therefore, we are motivated to develop a green and interpretable classifier called SLMBoost. The idea is to train a boosting model with the Subspace Learning Machine (SLM). 

Let’s start by looking at a single SLM. In each SLM, we will first identify a discriminant subspace by a series of feature selection techniques, including DFT, RFT, removing correlated features, etc. Then, each SLM will learn a linear regression model on the selected subspace. Figure 1 illustrates a single SLM. To sum up, a single SLM is a linear least square model that operates on a subspace.

Further, we ensemble SLMs in a boosting fashion, which involves training a sequence of SLMs. In this approach, an SLM is trained to correct the errors made by the previous SLMs. To achieve this, the training target of an SLM is the residual of the accumulated result from all the SLMs before it. Two key factors to make this boosting work are changing different features and data subsets. By using DFT/RFT, we can zoom in on different [...]

By |February 4th, 2024|News|Comments Off on MCL Research on SLMBoost Classifier|

Congratulations to Xuejing Lei for Passing Her Defense

Congratulations to Xuejing Lei for passing her defense. Xuejing’s thesis is titled “Green Image Generation and Label Transfer Techniques.” Her Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Aiichiro Nakano (Outside Member). The Committee members praised Xuejing’s novel contributions and her excellent presentation. Many thanks to our lab members for participating in her rehearsal and providing valuable feedback. MCL News team invited Xuejing for a short talk on her thesis and PhD experience, and here is the summary. We thank Xuejing for her kind sharing, and wish her all the best in the next journey. A high-level abstract of Xuejing’s thesis is given below:

”We designed several generative modeling solutions for texture synthesis, image generation, and image label transfer. Unlike deep-learning-based methods, Our developed generative methods address small model sizes, mathematical transparency, and efficiency in training and generation. We first presented an efficient and lightweight solution for texture synthesis, which can generate diverse texture images given one exemplary texture image. Then, we proposed a novel generative pipeline named GenHop and reformulated it to improve its efficiency and model sizes, yielding our final Green Image generation method. To demonstrate the generalization ability of our generative modeling concepts, we finally adapt it to an image label transfer task and propose a method called Green Image Label Transfer for unsupervised domain adaptation. ”

Xuejing shared her Ph.D. experience at MCL as follows :

I would like first to express my gratitude to Prof. Kuo for his guidance, patience, and unwavering support throughout this journey. His attitude and passion for research have been invaluable to my growth and success. We have been exploring new directions in this field. Since there were few works we could refer to, I experienced a difficult time when Prof. Kuo asked me to tangle [...]

By |January 28th, 2024|News|Comments Off on Congratulations to Xuejing Lei for Passing Her Defense|

Congratulations to Yifan Wang for Passing His Defense

Congratulations to Yifan Wang for passing his defense today. Yifan’s thesis is titled “Advanced Techniques for Green Image Coding via Hierarchical Vector Quantization.” His Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Aiichiro Nakano (Outside Member). The Committee members appreciated Yifan’s contributions to this field in solving a very challenging problem. MCL News team invited Yifan for a short talk on his thesis and PhD experience, and here is the summary. We thank Yifan for his kind sharing, and wish him all the best in the next journey. A high-level abstract of Yifan’s thesis is given below:

”We developed an image compression codec, “Green Image Codec,” which differs from the traditional intra-prediction/transform-based or deep learning-based codec. We aim to have a codec with low decoding complexity and reasonable performance. We utilize the multi-grid representation as the foundation for our vector quantization-based codec. We proposed several coding tools that were designed and specialized for VQ to improve the rate-distortion gain and reduce the coding complexity. Systemic RDO, which was missing from the traditional VQ-based codec, was added to our framework and relieved the burden of finding suitable coding parameters. We can perform better at a low bit rate compared to H.264 intra with similar complexity.”

Yifan shared his Ph.D. experience at MCL as follows :

“During my time at MCL, I am very grateful for Professor Kuo’s push, hard work, and wisdom; I learned a lot from him. Even though the Ph.D. life for my first year was struggling, the new research topic for VQ-based image coding with few previous references brought a lot of trouble. We made many trials and errors, and I almost lost confidence and motivation because of the difficulty of developing a new codec. However, Professor Kuo kept working hard and provided [...]

By |January 21st, 2024|News|Comments Off on Congratulations to Yifan Wang for Passing His Defense|

Welcome to Join MCL as an Intern Sanket Kumbhar

We are so happy to welcome a new graduate member,  Sanket Kumbhar, joining MCL as an intern. Here is a quick interview with Sanket:
1. Could you briefly introduce yourself and your research interests?

Hi, my name is Sanket Rajendra Kumbhar. I am a graduate student at USC, pursuing my Masters in Electrical Engineering. I completed my undergraduate studies in India and have two years of professional experience in Electrical Hardware. My primary research interests lie in Signal and Image processing, Machine Learning.
2. What is your impression about MCL and USC?
USC is renowned in various fields, including diverse research areas and athletic programs. It offers numerous opportunities for individuals to advance in their careers. MCL is one such place, where students are nurtured, trained, and equipped to achieve their career aspirations. The members at MCL are supportive, focused, and enthusiastic. The lab’s director, Professor Jay Kuo, inspires everyone with his hard work and passion for his work.
 3. What is your future expectation and plan in MCL?
For the Spring 2024 semester I will be working on the Green Learning approach for processing of multivariate time series with missing values. I am looking forward to continuing my contribution to ongoing research in Green Learning at MCL in the future.

By |January 14th, 2024|News|Comments Off on Welcome to Join MCL as an Intern Sanket Kumbhar|
  • Permalink Gallery

    MCL Research on PD-L1 Prediction in Clear Cell Renal Cell Carcinoma

MCL Research on PD-L1 Prediction in Clear Cell Renal Cell Carcinoma

Clear cell renal cell carcinoma (ccRCC) is the most common type of kidney cancer. Programmed Death-Ligand 1 (PD-L1) is an important prognostic marker for ccRCC and CT radiomics can be a non-invasive modality to predict PD-L1.

 

In a previous study by Shieh et al. [1], the research team explored using radiomic features from computer tomography (CT) imaging to predict the TIME measurements via mIHC analysis. Tumor specimens were categorized as positive or negative, guided by varying thresholds of PD-L1 expression of the tumor epithelium. A total of 1,708 radiomic features were extracted from CT images using a custom-built radiomics pipeline. To predict tumor binary classification based on these radiomic features.

 

Building upon this work [1], our study explored a novel approach known as Green Learning (GL).

As shown in Fig. 1, our study employs a modularized solution that includes the following modules: the DFT module for feature dimension reduction and the LNT module for new feature generation. Fig [2] presents the sorted DFT loss curve. The x-axis represents the sorted dimension index, while the y-axis represents the corresponding DFT loss value. The colored points scattered on the curve denote the DFT loss of the top 10 variables of importance (VOI), which are identified from the prior study [1]. All these top 10 VOIs possess relatively low DFT loss. The DFT loss value of LNT feature is the lowest among the raw features.

 

We observed a significant improvement in the radiomics prediction performance of tumor epithelium PD-L1 > 1%, >5% and >10%. Compared to prior research, the AUROC values improved from 0.61 to 0.76, 0.75 to 0.85 and 0.85 to 0.88, respectively.

 

[1] A. T.-W. Shieh, S. Y. Cen, B. Varghese, D. H. Hwang, X. Lei, K. Gurumurthy, I. Siddiqi, [...]

By |January 7th, 2024|News|Comments Off on MCL Research on PD-L1 Prediction in Clear Cell Renal Cell Carcinoma|

Happy New Year!

As we step into 2024, we want to wish all MCL members an amazing year ahead. May this year bring you lots of happiness, success, and the strength to chase your dreams fearlessly. Here’s to a fantastic year of growth and exciting opportunities for everyone in the MCL community!

 

Image credit: https://www.freepik.com/free-vector/happy-new-year-2024-background-with-elegant-luxury-golden numbers_67186845.htm#query=happy%20new%20year%202024&position=0&from_view=keyword&track=ais&uuid=776dff76-63c8-4a54-b5a7-275aff3f762e

By |December 30th, 2023|News|Comments Off on Happy New Year!|

Merry Christmas

In 2023, MCL has seen tremendous growth and success. With the departure of esteemed members who have graduated, their impactful research leaves a lasting legacy as they embark on new journeys. Simultaneously, new talent has joined our MCL family, eagerly immersing themselves in research endeavors.

Throughout this remarkable year, MCL members have dedicated themselves tirelessly to their research pursuits, resulting in exceptional publications in esteemed journals and conferences. We express our deepest gratitude for the unwavering commitment and commendable contributions of each member, transforming possibilities into remarkable achievements.

As we approach the festive season, filled with joy and camaraderie, we extend heartfelt Christmas wishes to all MCL members. May this holiday season bring warmth, happiness, and a sense of togetherness to each of you. Let’s not only celebrate the accomplishments of the past year but also cherish the unity and collaborative spirit that define our MCL family. Merry Christmas to all!

 

Image 1: https://pixabay.com/vectors/merry-christmas-holiday-pattern-6826522/

Image 2: https://pixabay.com/illustrations/christmas-tree-merry-christmas-card-1899904/

By |December 17th, 2023|News|Comments Off on Merry Christmas|

MCL Research on Camouflaged Object Detection

Camouflage detection is a pivotal area that relies on sophisticated algorithms and advanced models capable of discerning objects or individuals concealed within their environment by employing various camouflage techniques like pattern matching. These models play a crucial role in diverse domains such as security, wildlife monitoring, and even military applications, where their ability to distinguish foreground hidden objects from the background image pixels is paramount for effective detection and identification.

In our pursuit of enhancing camouflage detection capabilities, we have trained our model primarily on hidden animals. We have chosen to use the COD10K dataset [1]. This consists of 10,000 images, of which 5,066 are camouflaged, 3000 are background, and 1934 are non-camouflaged, which makes it a robust dataset very suitable for camouflage detection.

Currently, we have a GreenCOD[2] model designed with EfficientNet feature extraction and an upsampling structure of XGBoost to gradually predict the detection results. Our goal is to further reduce the model size and runtime, while potentially increasing the performance. In the future, we plan to use this improved model to analyze videos with hidden objects, like the MoCA-Mask dataset. This will help the model work well in real-time situations, like surveillance and protecting wildlife. Ultimately, we aim to enhance camouflage detection systems used in different fields.

 

 

[1] D. Fan, G. Ji, G. Sun, Ming-Ming Cheng, Jianbing Shen, Ling Shao. “Camouflaged Object Detection”. CVPR, 2020.

[2] H. Chen, Y. Zhu, S. You, C.-C. J. Kuo, “GreenCOD: Green Camouflaged Object Detection”. APSIPA Transactions on Signal and Information Processing 2023. Available: https://hongshuochen.com/GreenCOD/

Image credits:

Image showing image/mask pair of animal image is from [1].

Image showing the architecture of GreenCOD is from [2].

 

By |December 10th, 2023|News|Comments Off on MCL Research on Camouflaged Object Detection|

MCL Research on Least-Squares Normal Transform

In the ever-evolving realm of artificial intelligence (AI) and machine learning (ML), deep learning (DL) has reigned supreme for the past decade. However, its enigmatic nature and computational intricacies have prompted a quest for alternatives. Enter green learning (GL), a novel approach committed to constructing AI systems that are not just powerful but also interpretable, reliable, and sustainable.
GL is structured around three key modules: unsupervised representation learning, supervised feature learning, and supervised decision learning. Our primary focus is on the second module, which tackles the shortcomings of DL.

In the initial stages of GL, a diverse set of representations is crafted without any guiding supervision. These representations then undergo a discriminant feature test (DFT) in the subsequent module, where they are ranked based on their ability to discriminate. The selected discriminant representations become features. While the unsupervised nature of the first module might make GL representations seem less competitive than their DL counterparts, a remedy is proposed.

To address this, a novel approach emerges—creating new features through linear combinations of selected features. This method shows promise in obtaining more discriminant features, introducing a challenge of finding optimal weights for these combinations. Previous search algorithms like probabilistic search, adaptive particle swarm optimization (APSO) search, and stochastic gradient descent (SGD) search have been explored, but they still come with computational expenses.

Enter the least-squares normal transform (LNT), a game-changer. LNT is a supervised method designed to efficiently generate discriminant complementary features. These new features, termed complementary features, complement the original input features, referred to as raw features. The significance of this work lies in two key contributions: the introduction of LNT as an efficient tool for generating discriminant complementary features and its practical application, showcasing its prowess in [...]

By |December 3rd, 2023|News|Comments Off on MCL Research on Least-Squares Normal Transform|

Thanksgiving Luncheon

For more than two decades, the Thanksgiving Luncheon has been an unmissable tradition at MCL. A cherished gathering that brings the entire group together for a joyous meal. This year was no exception, as on November 23, 2023, the MCL family gathered at Shiki Seafood Buffet to celebrate this annual event.
The Thanksgiving Luncheon holds a special place in the hearts of all MCL members. It’s not just a meal; it’s a chance for the community to bond, laugh, and share in the spirit of gratitude. The food was not the only highlight of the day; it was the connections and conversations that truly enriched the gathering. As colleagues and friends sat together, conversations flowed effortlessly, fostering deeper connections and allowing everyone to unwind after a hectic semester.
The success of this cherished event wouldn’t have been possible without the dedicated efforts of Professor Kuo, whose vision and commitment brought everyone together, and the students, whose meticulous planning ensured a seamless and enjoyable experience for all.
Here’s to many more years of laughter, camaraderie, and cherished memories. Happy Thanksgiving!

By |November 26th, 2023|News|Comments Off on Thanksgiving Luncheon|