Internet-enabled smartphones and ultra-wide displays are transforming a variety of visual
apps spanning from on-demand movies and 360° videos to video-conferencing and live …

Along with the rapid developments in communication technologies and the surge in the use
of mobile devices, a brand-new computation paradigm, edge computing, is surging in …

Despite the soaring use of convolutional neural networks (CNNs) in mobile applications,
uniformly sustaining high-performance inference on mobile has been elusive due to the …

Remarkable achievements have been obtained by deep neural networks in the last several
years. However, the breakthrough in neural networks accuracy is always accompanied by …

Remarkable achievements have been attained with Generative Adversarial Networks
(GANs) in image-to-image translation. However, due to a tremendous amount of parameters …

Knowledge distillation, in which a student model is trained to mimic a teacher model, has
been proved as an effective technique for model compression and model accuracy boosting …

Abstract Knowledge distillation (KD) transfers the dark knowledge from cumbersome
networks (teacher) to lightweight (student) networks and expects the student to achieve …

This paper presents a survey of methods for pruning deep neural networks. It begins by
categorising over 150 studies based on the underlying approach used and then focuses on …

Adaptive optimization methods for deep learning adjust the inference task to the current
circumstances at runtime to improve the resource footprint while maintaining the model's …

To tackle the high inference latency exhibited by autoregressive language models, previous
studies have proposed an early-exiting framework that allocates adaptive computation paths …