In the field of natural language processing (NLP), there have been various pre-training
language models in recent years, with question answering systems gaining significant …

Current state-of-the-art remote sensing salient object detectors always require high-
resolution spatial context to ensure excellent performance, which incurs enormous …

Network pruning aims to compress models while minimizing loss in accuracy. With the
increasing focus on bias in AI systems, the bias inheriting or even magnification nature of …

Post-training quantization (PTQ) is widely regarded as one of the most efficient compression
methods practically, benefitting from its data privacy and low computation costs. We argue …

State-of-the-art deep learning models have a parameter count that reaches into the billions.
Training, storing and transferring such models is energy and time consuming, thus costly. A …

We present SPSRC, a novel, simple and effective framework to extract enhanced Structured
Pruning Saliency scores by Reorganizing Convolution. We observe that performance of …

Deep learning has achieved remarkable progress in various applications heightening the
importance of safeguarding the intellectual property (IP) of well-trained models. It entails not …

Image recognition is an important task in computer vision with broad applications. In recent
years, with the advent of deep learning, lightweight convolutional neural network (CNN) has …

Weight pruning is among the most popular approaches for compressing deep convolutional
neural networks. Recent work suggests that in a randomly initialized deep neural network …

The cumbersome computation of deep neural networks (DNNs) limits their practical
deployment on resource-constrained mobile multimedia devices. To deploy DNNs on …