Recent advancements in machine learning achieved by Deep Neural Networks (DNNs)
have been significant. While demonstrating high accuracy, DNNs are associated with a …

Large models based on the Transformer architecture play increasingly vital roles in artificial
intelligence, particularly within the realms of natural language processing (NLP) and …

Structured pruning and quantization are promising approaches for reducing the inference
time and memory footprint of neural networks. However, most existing methods require the …

Efficiency and trustworthiness are two eternal pursuits when applying deep learning in
practical scenarios. Considering efficiency, dataset distillation (DD) endeavors to reduce …

We introduce an efficient self-knowledge distillation framework, Dual Teachers for Self-
Knowledge Distillation (DTSKD), where the student receives self-supervisions by dual …

Model compression methods are being developed to bridge the gap between the massive
scale of neural networks and the limited hardware resources on edge devices. Since most …

Applying CNN on embedded systems is challenging due to model size limitations. Pruning
and quantization can help, but are time-consuming to apply separately. Our Single-Shot …

Arbitrary bit-width network quantization has received significant attention due to its high
adaptability to various bit-width requirements during runtime. However, in this paper, we …

Deep neural networks (DNNs) are ubiquitous in computer vision and natural language
processing, but suffer from high inference cost. This problem can be addressed by …

During recent years, deep convolutional neural networks have achieved remarkable
success in a wide range of sensor-based human activity recognition (HAR) applications …