Deep neural networks are generally designed as a stack of differentiable layers, in which a
prediction is obtained only after running the full stack. Recently, some contributions have …

The field of deep learning has witnessed significant progress, particularly in computer vision
(CV), natural language processing (NLP), and speech. The use of large-scale models …

Person re-identification (re-id) suffers from a serious occlusion problem when applied to
crowded public places. In this paper, we propose to retrieve a full-body person image by …

Shallow supervised 1-hidden layer neural networks have a number of favorable properties
that make them easier to interpret, analyze, and optimize than their deep counterparts, but …

The superior performance of modern computer vision backbones (eg, vision Transformers
learned on ImageNet-1 K/22 K) usually comes with a costly training procedure. This study …

The superior performance of modern deep networks usually comes with a costly training
procedure. This paper presents a new curriculum learning approach for the efficient training …

Recent advances in vision Transformers (ViTs) have come with a voracious appetite for
computing power, high-lighting the urgent need to develop efficient training methods for …

In this paper, we propose a robust method for semisupervised training of deep neural
networks for multi-label image classification. To this end, we use ramp loss, which is more …

Deep neural networks (DNNs) typically have a single exit point that makes predictions by
running the entire stack of neural layers. Since not all inputs require the same amount of …

Seismic image analysis plays a crucial role in a wide range of industrial applications and
has been receiving significant attention. One of the essential challenges of seismic imaging …