Given a pre-trained BERT, how can we compress it to a fast and lightweight one while maintaining its accuracy? Pre-training language model, such as BERT, is effective for improving the performance of natural language processing (NLP) tasks. However, ...
Pneumothorax is a common injury in disaster rescue, traffic accidents, and war trauma environments and requires early diagnosis and treatment. The commonly used X-ray, CT, and other diagnostic instruments are not suitable for rescue sites due to thei...
Despite the great progress in 3D pose estimation from videos, there is still a lack of effective means to extract spatio-temporal features of different granularity from complex dynamic skeleton sequences. To tackle this problem, we propose a novel, s...
Neural networks : the official journal of the International Neural Network Society
35344706
Deep Neural Networks (DNNs) have been vastly and successfully employed in various artificial intelligence and machine learning applications (e.g., image processing and natural language processing). As DNNs become deeper and enclose more filters per l...
BACKGROUND: Digital breast tomosynthesis (DBT) is a technique that can overcome the shortcomings of conventional X-ray mammography and can be effective for the early screening of breast cancer. The compression of the breast is essential during the DB...
Federated learning is a privacy-preserving machine learning technique to train intelligent models from decentralized data, which enables exploiting private data by communicating local model updates in each iteration of model learning rather than the ...
It is hard to directly deploy deep learning models on today's smartphones due to the substantial computational costs introduced by millions of parameters. To compress the model, we develop an ℓ0-based sparse group lasso model called MobilePrune which...
Neural networks : the official journal of the International Neural Network Society
35609502
Model pruning is widely used to compress and accelerate convolutional neural networks (CNNs). Conventional pruning techniques only focus on how to remove more parameters while ensuring model accuracy. This work not only covers the optimization of mod...
Compressive sensing (CS) is a sub-Nyquist sampling framework that has been employed to improve the performance of numerous imaging applications during the last 15 years. Yet, its application for large and high-resolution imaging remains challenging i...
Convolutional Neural Networks (CNNs) are popular models that are widely used in image classification, target recognition, and other fields. Model compression is a common step in transplanting neural networks into embedded devices, and it is often use...