EACP: An effective automatic channel pruning for neural networks

Y Liu, D Wu, W Zhou, K Fan, Z Zhou - Neurocomputing, 2023 - Elsevier
The large data scale and computational resources required by Convolutional Neural
Networks (CNNs) hinder the practical application on mobile devices. However, channel …

Survey of different large language model architectures: Trends, benchmarks, and challenges

M Shao, A Basit, R Karri, M Shafique - IEEE Access, 2024 - ieeexplore.ieee.org
Large Language Models (LLMs) represent a class of deep learning models adept at
understanding natural language and generating coherent text in response to prompts or …

Overcoming limitation of dissociation between MD and MI classifications of breast cancer histopathological images through a novel decomposed feature-based …

M Sepahvand, F Abdali-Mohammadi - Computers in Biology and Medicine, 2022 - Elsevier
Magnification-independent (MI) classification is considered a promising method for detecting
the histopathological images of breast cancer. However, it has too many parameters for real …

Model compression and efficient inference for large language models: A survey

W Wang, W Chen, Y Luo, Y Long, Z Lin… - arXiv preprint arXiv …, 2024 - arxiv.org
Transformer based large language models have achieved tremendous success. However,
the significant memory and computational costs incurred during the inference process make …

Ded: Diagnostic evidence distillation for acne severity grading on face images

Y Lin, J Jiang, D Chen, Z Ma, Y Guan, X Liu… - Expert Systems with …, 2023 - Elsevier
Acne seriously affects people's daily life. Acne severity level grading plays a decisive role in
the cure. However, the acne criterion is not unified in the medical field. Most of the current …

SRT: Improved transformer-based model for classification of 2D heartbeat images

W Wu, Y Huang, X Wu - Biomedical Signal Processing and Control, 2024 - Elsevier
Electrocardiography (ECG) is a crucial tool for diagnosing cardiovascular diseases. In
particular, combining clinical ECG with computer technology for automatic ECG analysis can …

MPQ-YOLO: Ultra low mixed-precision quantization of YOLO for edge devices deployment

X Liu, T Wang, J Yang, C Tang, J Lv - Neurocomputing, 2024 - Elsevier
Abstract You Only Look Once (YOLO), known for its real-time performance and outstanding
accuracy, has emerged as a prominent framework for object detection tasks. However …

Efficient training and inference: Techniques for large language models using llama

SR Cunningham, D Archambault, A Kung - Authorea Preprints, 2024 - techrxiv.org
To enhance the efficiency of language models, it would involve optimizing their training and
inference processes to reduce computational demands while maintaining high performance …

Differentiated knowledge distillation: Patient-specific single-sample personalization for electrocardiogram diagnostic models

X Wei, Z Li, Y Tian, M Wang, J Liu, Y Jin, W Ding… - … Applications of Artificial …, 2024 - Elsevier
To achieve optimal performance in practical applications, the electrocardiogram (ECG)
diagnosis models have to be personalized using the ECG data of specific patients. Most …

[PDF][PDF] 基于改进YOLO v5s 的经产母猪发情检测方法研究

薛鸿翔, 沈明霞, 刘龙申, 陈金鑫, 单武鹏, 孙玉文 - 农业机械学报, 2023 - aeeisp.com
为解决限位栏场景下经产母猪查情难度大, 过于依赖公猪试情和人工查情的问题,
提出了一种基于改进YOLO v5s 算法的经产母猪发情快速检测方法. 首先, 利用马赛克增强方式 …