In recent years, deep learning (DL) models have demonstrated remarkable achievements
on non-trivial tasks such as speech recognition, image processing, and natural language …

Recent advancements in deploying deep neural networks (DNNs) on resource-constrained
devices have generated interest in input-adaptive dynamic neural networks (DyNNs) …

Most state-of-the-art deep neural networks use static inference graphs, which makes it
impossible for such networks to dynamically adjust the depth or width of the network …

Multi-exit architectures, in which a sequence of intermediate classifiers are introduced at
different depths of the feature layers, perform adaptive computation by early exiting``easy" …

Rescue vessels are the main actors in maritime safety and rescue operations. At the same
time, aerial drones bring a significant advantage into this scenario. This paper presents the …

Accurate segmentation of corneal layers depicted on optical coherence tomography (OCT)
images is very helpful for quantitatively assessing and diagnosing corneal diseases (eg …

Deep Learning (DL) provided powerful tools for various visual information analysis and
retrieval tasks, outperforming previously used methods. However, despite the potential of …

This article summarizes principles and ideas from the emerging area of applying conditional
computation methods to the design of neural networks. In particular, we focus on neural …

By adding exiting layers to the deep learning networks, early exit can terminate the inference
earlier with accurate results. However, the passive decision-making of whether to exit or …

In computer vision applications, mobile devices can transfer the inference of Convolutional
Neural Networks (CNNs) to the cloud due to their computational restrictions. Nevertheless …