Deep learning has recently achieved great success in many visual recognition tasks.
However, the deep neural networks (DNNs) are often perceived as black-boxes, making …

Fast and robust small target detection is one of the key technologies in the infrared (IR)
search and tracking systems. With the development of deep learning, there are many data …

Large language models have been widely adopted but require significant GPU memory for
inference. We develop a procedure for Int8 matrix multiplication for feed-forward and …

This chapter provides approaches to the problem of quantizing the numerical values in deep
Neural Network computations, covering the advantages/disadvantages of current methods …

Deep neural networks have been applied in many applications exhibiting extraordinary
abilities in the field of computer vision. However, complex network architectures challenge …

Internet of Things (IoT) can help to pave the way to the circular economy and to a more
sustainable world by enabling the digitalization of many operations and processes, such as …

The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …

Stateful optimizers maintain gradient statistics over time, eg, the exponentially smoothed
sum (SGD with momentum) or squared sum (Adam) of past gradient values. This state can …

Deep learning models are vulnerable to adversarial examples. As a more threatening type
for practical deep learning systems, physical adversarial examples have received extensive …

Weight and activation binarization is an effective approach to deep neural network
compression and can accelerate the inference by leveraging bitwise operations. Although …