News

Welcome New MCL Member Qi Cao

We are very happy to welcome a new MCL member, Qi Cao. Here is a quick interview with Qi:

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

My name is Qi Cao, and I’m currently a PhD student in the ECE department at USC. I joined the MCL at the end of 2024. My research interests span machine learning, computer vision, and time-series analysis. Since joining MCL, I’ve been eager to contribute to ongoing projects, collaborate with lab members who have diverse technical backgrounds, and continue refining my skills through both hands-on experiments and regular discussions.

2. What is your impression of MCL and USC?

MCL comes across as a supportive, close-knit lab where the collaborative atmosphere helps make challenging projects feel manageable. USC strikes me as the kind of campus that buzzes with energy—entrepreneurial, diverse, and always open to new perspectives.

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

I’m looking forward to collaborating closely with everyone in MCL,  sharing ideas during group meetings, and learning from the lab’s diverse expertise. I hope to contribute actively to interesting projects by participating in regular discussions and offering support whenever it’s needed. I aim to both grow my own skills and help the whole team move our research forward.

By |June 1st, 2025|News|Comments Off on Welcome New MCL Member Qi Cao|

MCL Research on Image Classification

Image classification is a key task in computer vision, typically driven by high-performing deep learning methods. However, these methods are criticized for lacking transparency. As an alternative, Green Learning offers more interpretable models, though their performance is not as strong as that of deep learning.

We propose a novel Green Learning framework that enhances performance by integrating label supervision directly into the feature extraction process. A key component of our approach is the LDA filter block, which is a feedforward mechanism that uses Linear Discriminant Analysis (LDA) to create convolution filters without the need for backpropagation. Additionally, we present spectral LNT, a new variant of the least-squares normal transform (LNT) that takes advantage of the spatial-spectral structure of feature maps by applying localized linear combinations of features. Together, our methods create a label-guided, interpretable feature extraction pipeline.

By |May 25th, 2025|News|Comments Off on MCL Research on Image Classification|

Congratulations to Wei Wang for Passing Her Defense!

Congratulations to Wei Wang for passing her defense today. Wei’s thesis title is “Explainable and Lightweight Machine Learning Models for Image Super-Resolution and Denoising.” Her Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Jernej Barbic (Outside Member). The Committee members were pleased with Wei’s thesis work. Here is a summary of her thesis:Image signal processors convert camera sensor data into images via digital image processing operations. In recent years, we have witnessed an increased interest in using Deep Learning to enhance the ISP raw images for improved quality. The main challenge is the regularization of this ill-posed problem.

Practically, the trade-off between quality improvement and the computational complexity is the key issue of widely applying the existing state-of-the-art methods. In this dissertation defense talk, we propose effective and efficient techniques for the typical low-level image enhancement problem, image super-resolution (SR) based Green Learning. First, we propose LSR and LSR++, a light-weight super-resolution green learning method with feedforward design without backpropagation, and its advanced version with significantly smaller computational complexity. Second, we develop Green U-Shaped Learning (GUSL) method for super-resolution with multi-level coarse-to-fine semantic estimation and effective conditional residual prediction. Third, we introduce Green U-Shaped Learning method to medical computed tomography (CT) images for low-dose CT image denoising enhancement to demonstrate its generalization capability. All above, these methods contribute to advanced efficiency with competitiveperformance, mathematical transparency, and robust generalizability in low-level computer vision problems.

Wei generously shared her experiences in the MCL Lab with us: It has been a long journey. First and foremost, I would like to extend my sincere thanks to my Ph.D. advisor, Professor C.-C. Jay Kuo, for his outstanding mentorship and consistent support throughout my doctoral journey. His dedication to research, strong work ethic, and sense [...]

By |May 18th, 2025|News|Comments Off on Congratulations to Wei Wang for Passing Her Defense!|
  • Permalink Gallery

    Congratulations to Qingyang Zhou  for Passing His Defense!

Congratulations to Qingyang Zhou  for Passing His Defense!

Congratulations to Qingyang Zhou on successfully defending his dissertation today! His thesis, titled “Advanced Techniques for Point Cloud Quality Assessment, Surface Reconstruction, and Coding,” was reviewed by his committee—chaired by Jay Kuo, with Antonio Ortega as a member and Stefanos Nikolaidis serving as the outside examiner. The committee praised the rigor and excellence of Qingyang’s research. Here is a summary of his thesis:Point clouds (PCs) play a critical role in 3D vision and graphics applications such as AR/VR, digital preservation, and medical imaging. However, their large data volume, vulnerability to quality degradation, and the need for surface reconstruction from sparse, noisy points pose long-standing challenges. In this work, we address these issues through three research thrusts: compression, quality assessment, and surface reconstruction. First, we propose GPCGC, a low-complexity geometry compression method that leverages vector quantization and block-level rate-distortion modeling to achieve fast encoding/decoding with competitive performance. Second, we introduce GPQA, an interpretable, saliency-guided quality assessment framework that projects local 3D structures into 2D patches and uses a green machine learning model to predict perceptual quality under both full- and no-reference settings. Third, we develop two surface reconstruction methods: GPSR, an unsupervised diffusion-based approach, and LPSR, a supervised variant under the green learning paradigm. Together, these contributions advance the efficiency, interpretability, and robustness of the point cloud processing pipeline, enabling practical deployment in resource-constrained environments.He generously shared his experiences in the MCL Lab with us:My PhD journey at the University of Southern California’s Media Communications Lab (MCL) has been one of the most rewarding chapters of my life. Under the guidance of Professor C.-C. Jay Kuo, and with the generous support of MCL alumni and lab members, I not only deepened my technical knowledge but [...]

By |May 11th, 2025|News|Comments Off on Congratulations to Qingyang Zhou  for Passing His Defense!|

MCL Research on Prostate Segmentation

Automatic segmentation of the prostate is a crucial step in the computer-aideddiagnosis of prostate cancer and in treatment planning. Current methods for prostatesegmentation primarily rely on deep learning models with neural networks. However,these models tend to be large and lack transparency, which is essential forphysicians. We proposed a new data-driven 3D prostate segmentation method onMRI named Green U-shaped Learning (GUSL). Different from deep learning basedmethods, GUSL employs a feed-forward system that utilizes successive subspacelearning (SSL).To keep enough detailed information on a dataset with a large image size, wepropose a cascading model in two stages, as shown in Figure 1: (1) segmentation ondownsampled images and (2) segmentation on the cropped patches. GUSL consistsof three main modules, as shown in Figure 2: representation learning, featurelearning, and residual correction. All modules are applied at multiple levels withvarying resolutions. We achieve fine-to-coarse unsupervised representation learning

using cascaded VoxelHop units, as well as coarse-to-fine segmentation throughfeature learning and residual correction. GUSL maintains a very competitive standingperformance-wise with other DL baseline models and keeps a smaller model sizeand less complexity, with transparency for doctors.

By |May 4th, 2025|News|Comments Off on MCL Research on Prostate Segmentation|

MCL Research on Green Image Super-resolution

Single image super-resolution (SISR) is an intensively studied topic in image processing. It aims at recovering a high-resolution (HR) image from its low-resolution (LR) counterpart. SISR finds wide real-world applications such as remote sensing, medical imaging, and biometric identification. Besides, it attracts attention due to its connection with other tasks (e.g., image registration, compression, and synthesis). 

The main challenge of SISR is the ill-pose issue. We recently have been developing a solution by providing reasonable performance and effectively reduced complexity. We propose a green U-shape method to progressively enhance the LR images from global structure to local details with increasing spatial sizes and conditional residual estimation. 

By |April 27th, 2025|News|Comments Off on MCL Research on Green Image Super-resolution|

MCL Research on Nuclei Segmentation

Nuclei Segmentation is a key step in understanding the distribution, size, and shape of nuclei in the underlying tissue. Traditionally, pathologists view histology slides under the microscope to analyze the nuclear structure. However, this process is time-consuming and is prone to inter-reader variability. An AI-based segmentation algorithm can aid pathologists in cancer detection and prognosis, and help speed up the cancer screening procedure. 

While there are several deep learning methods addressing this problem, we propose a Green Nuclei Segmentation algorithm that uses a simple, reliable, and modular approach to delineate nuclei in a histopathology slide. The Green U-shaped Learning(GUSL) is a 4 level pipeline that involves three main modules: representation learning using PixelHop, feature selection using RFT, and supervised learning using XGBoost Regressor. The different levels help look at the histopathology image at multiple resolutions, while we attempt to segment the nuclei in a coarse to fine manner. At each level, we aim to correct the previous layer’s predictions through residue correction. While this model gives good results, we can further improve the performance by refining the boundary regions to yield precise nuclei contours. 

By |April 20th, 2025|News|Comments Off on MCL Research on Nuclei Segmentation|

MCL Research on Seismic Data Processing

Seismic waves are mechanical waves generated by earthquakes that travel through the Earth. Body waves consist of fast, compressional primary (P) waves and slower, shear secondary (S) waves. With large datasets of seismogram recordings, researchers train machine learning models to automatically pinpoint P‑ and S‑wave arrival times. This is essential for real‑time seismic monitoring and early warning systems.

Our Green Learning framework streamlines this process while boosting interpretability. We begin by slicing raw seismic recordings into overlapping three‑channel windows and assigning each a continuous pseudo‑label (ranging from 0 to 1) that reflects how accurately it is aligned to a P‑ or S‑wave onset. Treating these windows as 3‑channel images, we extract multi‑scale features via multiple Saab transform layers and select the most powerful features at each scale using Relevant Feature Test (RFT) modules. An XGBoost regressor then produces a continuous output signal, from which P‑ and S‑wave arrivals are simply recovered by peak detection. Compared to the SotA deep learning model EQTransformer, this model uses far fewer parameters,

By |April 13th, 2025|News|Comments Off on MCL Research on Seismic Data Processing|

MCL Research on Image Denoising

Image denoising is a computer vision technique that removes noise from images while preserving essential structures and textures. It plays a critical role in applications such as photography enhancement, medical imaging, and remote sensing.

To address such problems, we have employed GUSL, a Green Learning-based pipeline tailored for image denoising. Noisy images are resized to multiple resolutions, and Green Learning techniques such as PixelHop, RFT, and LNT are applied at each level to extract features independently. Each level progressively refines the denoising result by correcting the residuals from the previous level. While this approach yields promising results, further refinement is needed to enhance performance in smooth and texture-rich regions.

By |April 6th, 2025|News|Comments Off on MCL Research on Image Denoising|

MCL Research on Video-Text Retrieval

Image-text retrieval is a fundamental task in image understanding. This task aims to retrieve the most relevant information from another modality based on the given image or text. Recent approaches focus on training large neural networks to bridge the gap between visual and textual domains. However, these models are computationally expensive and not explainable regarding how the data from different modalities are aligned. End-to-end optimized models, such as large neural networks, can only output the final results, making it difficult for humans to understand the reasoning behind the model’s predictions.

Hence, we propose a green learning solution, Green Multi-Modal Alignment (GMA), for computational efficiency and mathematical transparency. We reduce trainable parameters to 3% compared to fine-tuning the whole image and text encoders. The model is composed of three modules, including (1) Clustering, (2) Feature Selection, and (3) Alignment. The clustering process divides the whole dataset into subsets by choosing similar image and text pairs, reducing the training sample’s divergence. The second module, feature selection, reduces the feature dimension and mitigates the computational requirements. The importance of each feature can be interpreted as statistical evidence supporting our reasoning. The alignment is conducted by linear projection, which guarantees the inverse projection in both direction retrievals, namely image-to-text and tex-to-image retrievals.

Experimental results show that our model can outperform the SOTA retrieval models in text-to-image and image-to-text retrieval on the Flick30k and MS-COCO datasets. Besides, our alignment process can incorporate visual and text encoder models trained separately and generalize well to unseen image-text pairs.

By |March 30th, 2025|News|Comments Off on MCL Research on Video-Text Retrieval|