TGHop: an explainable, efficient, and lightweight method for texture generation

Lei, Xuejing; Zhao, Ganning; Zhang, Kaitai; Kuo, C.‐C. Jay

doi:10.1017/atsip.2021.15

Cited by 9 publications

(3 citation statements)

References 42 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…image generation [16][17][18], blind image quality assessment [19], disease classification [20], face gender classification [21], and object tracking [22][23][24].…”

Section: (I)mentioning

confidence: 99%

Methodology of soft partition for image classification

Mishra,

Kuo

2024

Disruptive Technologies in Information Sciences VIII

View full text Add to dashboard Cite

The idea of subspace learning machine (SLM) has been a powerful tool for machine learning (ML), and it has been successfully applied to the task of image classification. Recently, a novel SLM method was proposed, which (i) projects high-dimensional feature vectors into a 1D feature subspace, and (ii) partitions it into two disjoint sets. SLM with soft partitioning (SLM/SP) extends this approach by learning an adaptive soft decision tree (SDT) structure using local greedy subspace partitioning. After meeting the stopping criteria for all child nodes and determining the tree structure, it updates all projection vectors (PVs) globally. It enables efficient training, high classification accuracy, and a small model size. It is applied to experimental data to show its performance as a lightweight and high-performance classification method.

show abstract

“…image generation [16][17][18], blind image quality assessment [19], disease classification [20], face gender classification [21], and object tracking [22][23][24].…”

Section: (I)mentioning

confidence: 99%

Methodology of soft partition for image classification

Mishra,

Kuo

2024

Disruptive Technologies in Information Sciences VIII

View full text Add to dashboard Cite

show abstract

“…Examples of green learning models include PixelHop [39] and PixelHop++ [40] for object classification and PointHop [41] and PointHop++ [42] for 3D point cloud classification. Green learning techniques have been developed for many applications such as deepfake detection [43], anomaly detection [44], image generation [45], etc. We propose a lightweight BIQA method in this work by following this path.…”

Section: Green Machine Learningmentioning

confidence: 99%

Lightweight High-Performance Blind Image Quality Assessment

Mei¹,

Wang²,

He³

et al. 2023

Preprint

View full text Add to dashboard Cite

Blind image quality assessment (BIQA) is a task that predicts the perceptual quality of an image without its reference. Research on BIQA attracts growing attention due to the increasing amount of user-generated images and emerging mobile applications where reference images are unavailable. The problem is challenging due to the wide range of content and mixed distortion types. Many existing BIQA methods use deep neural networks (DNNs) to achieve high performance. However, their large model sizes hinder their applicability to edge or mobile devices. To meet the need, a novel BIQA method with a small model, low computational complexity, and high performance is proposed and named "GreenBIQA" in this work. GreenBIQA includes five steps: 1) image cropping, 2) unsupervised representation generation, 3) supervised feature selection, 4) distortionspecific prediction, and 5) regression and decision ensemble. Experimental results show that the performance of GreenBIQA is comparable with that of state-of-the-art deep-learning (DL) solutions while demanding a much smaller model size and significantly lower computational complexity.

show abstract

“…Such a characteristic is particularly appealing under edge-cloud collaboration as individual modules can be optimized at the user devices with minimum memory requirement and carbon footprint. Green GenAI models have been explored in the last several years, e.g., NITES [70], TGHop [71], Pager [6], GENHOP [69]. These models are very attractive at the edges.…”

Section: Green Generative Ai Modelsmentioning

confidence: 99%

An Overview on Generative AI at Scale With Edge–Cloud Computing

Wang,

Xue,

Wei

et al. 2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

As a specific category of artificial intelligence (AI), generative artificial intelligence (GenAI) generates new content that resembles what humans create. The rapid development of GenAI systems has created a huge amount of new data on the Internet, posing new challenges to current computing and communication frameworks. Currently, GenAI services rely on the traditional cloud computing framework due to the need for large computation resources. However, such services will encounter high latency because of data transmission and a high volume of user requests. On the other hand, edge-cloud computing can provide adequate computation power and low latency at the same time through the collaboration between edges and the cloud. Thus, it is attractive to build GenAI systems at scale by leveraging the edge-cloud computing paradigm. In this overview paper, we review recent developments in GenAI and edge-cloud computing, respectively. Then, we use two exemplary GenAI applications to discuss technical challenges in scaling up their solutions using edge-cloud collaborative systems. Finally, we list design considerations for training and deploying GenAI systems at scale and point out future research directions.

show abstract

TGHop: an explainable, efficient, and lightweight method for texture generation

Cited by 9 publications

References 42 publications

Methodology of soft partition for image classification

Methodology of soft partition for image classification

Lightweight High-Performance Blind Image Quality Assessment

An Overview on Generative AI at Scale With Edge–Cloud Computing

Contact Info

Product

Resources

About