News

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|

Congratulations to Hongyu Fu for Passing His Defense

Congratulations to Hongyu Fu for passing his defense today. Hongyu’s thesis is titled “Efficient Machine Learning Techniques for Low- and High-Dimensional Data Sources.” His Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Aiichiro Nakano (Outside Member). The Committee members were very pleased with Hongyu’s high-quality work and professional presentation skills. MCL News team invited Hongyu for a short talk on her thesis and PhD experience, and here is the summary. We thankHongyu for his kind sharing, and wish him all the best in the next journey. A high-level abstract of Hongyu’s thesis is given below:

“This thesis concentrates on the development of efficient machine learning methodologies for both low and high-dimensional data. It presents a novel, feature-based machine learning technique, noted the Subspace Learning Machine (SLM), specifically designed for low-dimensional data. SLM combines the efficiency of decision trees and the effectiveness of multi-layer perceptrons to solve classification and regression problems with high performance and low model complexity. For high-dimensional data, the thesis proposes an efficient feed-forward machine learning framework and an adaptive SLM design with soft partitioning for image classification. These methods offer lightweight, adaptive models with low computational requirements and high performance.”
Hongyu shared his Ph.D. experience at MCL as follows :
“My PhD experience at the USC Media Communications Lab under the guidance of Prof. Kuo was both challenging and rewarding, providing me with a solid foundation in machine learning and multimedia data processing. The PhD training at MCL with the weekly report and seminar series was quite unique,  we practiced clear summarization ability, writing skills, and sharpened our presentation and oral communication abilities extensively. Prof. Kuo was extremely energetic, and working with constantly high efficiency, with more than 10 students in the [...]

By |November 19th, 2023|News|Comments Off on Congratulations to Hongyu Fu for Passing His Defense|

Congratulations to Max Chen for Passing His Defense

Congratulations to Max Chen for passing his defense today. Max’ thesis is titled “A Green Learning Approach to Deepfake Detection and Camouflage and Splicing Object Localization.” His Dissertation Committee includes Jay Kuo (Chair), Shrikanth Narayanan, and Aiichiro Nakano (Outside Member). The Committee members highly praised the quality of his work. MCL News team invited Max for a short talk on her thesis and PhD experience, and here is the summary. We thank Max for his kind sharing, and wish him all the best in the next journey.

“In the current technological era, the advancement of AI models has not only driven innovation but also heightened concerns over environmental sustainability due to increased energy and water usage. For context, the water consumption equivalent to a 500ml bottle is tied to 10 to 50 responses from a model like GPT-3, and projections suggest that by 2027, AI could be using an estimated 85 to 134 TWh per year, potentially surpassing the water withdrawal of half of the United Kingdom. In light of these challenges, there is an urgent call for AI solutions that are environmentally friendly, characterized by lower energy consumption through fewer floating-point operations (FLOPs), more compact designs, and the ability to run independently on mobile devices without depending on server-based infrastructures.

This thesis introduces a novel approach for Camouflaged Object Detection, termed “GreenCOD.” GreenCOD combines the power of Extreme Gradient Boosting (XGBoost) with deep features. Contemporary research often focuses on devising intricate DNN architectures to enhance the performance of Camouflaged Object Detection. However, these methods are typically computationally intensive and show marginal differences between models. Our GreenCOD model stands out by employing gradient boosting for detection tasks. With its efficient design, it requires fewer parameters and FLOPs [...]

By |November 12th, 2023|News|Comments Off on Congratulations to Max Chen for Passing His Defense|
  • Permalink Gallery

    MCL Research on Subspace Learning Machine with Soft Partitioning (SLM/SP)

MCL Research on Subspace Learning Machine with Soft Partitioning (SLM/SP)

Feature extraction and decision-making are two modules in cascade in the classical pattern recognition (PR) or machine learning (ML) paradigm. We recently proposed a novel learning diagram named Subspace Learning Machine (SLM) which considers this learning paradigm and focus on specific modules for classification-oriented decision making. SLM can be viewed as a generalized version of Decision Tree (DT). The linear combination of multiple features can be written as the inner product of a projection
vector and a feature vector. The effectiveness of SLM depends on the selection of good projection vectors, e.g. when the projection vector is a one-hot
vector, SLM is nothing but DT.

Both SLM and DT apply a hard split to a feature using a threshold at a decision node. To overcome the cons of hard feature space partitioning, we propose a new SLM method that adopts soft partitioning and denote it with SLM/SP in this proposed work. A comparison between hard decision and soft decision is illustrated in Fig 1. SLM/SP adopts the soft decision tree (SDT) data structure and a novel topology is proposed with inner nodes of SDT for data routing, leaf nodes of SDT for local decision making, and edge between parent and child nodes for representation learning. Specific modules are designed for the nodes and edges, respectively. The training of a SLM/SP tree starts by learning an adaptive tree structure via local greedy exploration between subspace partitioning and feature subspace learning. The tree structure is finalized once the stopping criteria are met for all
leaf nodes, and all module parameters are updated globally.

The overall frame working using Successive Subspace Learning and SLM/SP for image classification is as shown in Fig 2. The structure of the SLM/SP tree [...]

By |November 5th, 2023|News|Comments Off on MCL Research on Subspace Learning Machine with Soft Partitioning (SLM/SP)|

MCL Research on Green Image Demosaicing

Demosaicing is a crucial step in the process of converting raw image data captured by sensors with Bayer color filter arrays into a full-color image that humans can perceive. Bayer arrays are a type of color filter array commonly used in digital image sensors, named after Bryce Bayer, who patented the design. These arrays consist of a grid of photosites, each covered by a color filter—typically red, green, or blue. Please see Figure 1.

Demosaicing in real-world scenarios poses a significant challenge due to the emergence of artifacts caused by factors such as sensor noise, motion blur, and edge artifacts. Sensor noise, introduced during image acquisition, can manifest as color noise, luminance noise, and texture loss in demosaiced images.

Another hurdle in demosaicing involves the necessity for ground truth data. Obtaining precise RGB images for training machine learning-based demosaicing methods is time-consuming, requiring meticulous alignment and synchronization across multiple color channels. To overcome this challenge, our strategy involves leveraging synthetic data generation, data augmentation, and domain adaptation techniques to augment the training dataset and mitigate the constraints of limited training data. We also consider semi-supervised learning as a viable approach for demosaicing.

In our investigation of the semi-supervised representation-learning module, we delve into a novel form of representation termed “oriented line segments (OLS),” illustrated in Figure 2. The OLS introduces two key hyperparameters: the length of a line segment, denoted as (2l+1), and the angle formed between two consecutive line segments.

The computational complexity of advanced demosaicing algorithms presents another challenge, particularly for real-time applications on resource-constrained devices like mobile phones or embedded systems. To address this, we propose the utilization of regression-based methods. This involves extracting and processing small image patches during demosaicing to learn the ground [...]

By |October 31st, 2023|News|Comments Off on MCL Research on Green Image Demosaicing|

Congratulations to Joe Wang for Passing His Defense

Congratulations to Joe Wang for passing his defense. Joe’s thesis is titled “Green Knowledge Graph Completion and Scalable Generative Content Delivery.” His Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Robin Jia (Outside Member). MCL News team invited Joe for a short talk on her thesis and PhD experience, and here is the summary. We thank Joe for his kind sharing, and wish her all the best in the next journey.

Knowledge graphs (KGs) and Generative AI (GenAI) models have powerful reasoning capabilities and are crucial for building advanced artificial intelligence (AI) systems. In my thesis, we focus on four fundamental research to improve the efficiency, scalability, and explainability of the existing methods. They are:
1. Improving KG Embeddings with Entity Types: Entity types describe the high-level taxonomy and categorization of entities in KGs. They are often ignored in KG embedding learning. Thus, we propose a new methodology to incorporate entity types to improve KG embeddings. Specifically, our method can represent entities and types in the same embedding space with a constant number of additional model parameters. In addition, our method has a huge advantage in computation efficiency during inference.
2. KG Completion with Classifiers: KG embeddings have limited expressiveness in modeling relations. Thus, we study using binary classifiers to represent relations in the KG completion task. There are several advantages to modeling missing links as a binary classification problem, including having access to more powerful classifiers and data augmentation.
3. Green KG Completion: KG completion methods often require higher embedding dimensions for good performance. Thus, we investigate applying feature transformation and univariate feature selection to reduce the feature dimensions in KG completion methods. The KGs are first partitioned into several groups to extract [...]

By |October 23rd, 2023|News|Comments Off on Congratulations to Joe Wang for Passing His Defense|

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).To deal with such ill-posed problem, we recently proposed two methods, LSR[1] and LSR++[2], by providing reasonable performance and effectively reduced complexity. LSR consists of three cascaded modules:
1) Unsupervised Representation Learning by creating a pool of rich and diversified representations in the neighborhood of a target pixel,
2) Supervised Feature Learning by Relative Feature Test (RFT [3]) to select a subset from the representation pool that is most relevant to the underlying super-resolution task automatically, and
3) Supervised Decision Learning by predicting the residual of the target pixel based on the selected features through regression via classical machine learning, and effectively fusioning the predictions for more stable results. LSR++ is promoted based on LSR, with emphasis on sample alignment, a more promising sample preparation process which is suitable for all patch-based computer vision problems. As illustrated in Fig 1, based on gradient histograms of patches along the eight reference directions (Fig.1.a), patch alignment utilizes patch rotations and flipping to meet the standard templates of gradient histograms, where D_max is the direction with the largest cumulative gradient magnitude, and D_max_orth_b and D_max_orth_s refer to the orthogonal directions to D_max with big and small cumulative gradient magnitude, respectively. By modifying the set of (D_max, D_max_orth_b, and D_max_orth_s) of a patch, patch alignment can regularize the edge pattern with the patch by directions perpendicular the edge (D_max) and directions along [...]

By |October 23rd, 2023|News|Comments Off on MCL Research on Green Image Super-resolution|