Related papers: ResNet strikes back: An improved training procedur…

We regard pre-trained residual networks (ResNets) as nonlinear systems and use linearization, a common method used in the qualitative analysis of nonlinear systems, to understand the behavior of the networks under small perturbations of the…

Despite the rapid progress of neuromorphic computing, inadequate capacity and insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice. Residual learning and shortcuts have…

Deep residual networks (ResNets) made a recent breakthrough in deep learning. The core idea of ResNets is to have shortcut connections between layers that allow the network to be much deeper while still being easy to optimize avoiding…

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We…

Many researchers believe that ConvNets perform well on small or moderately sized datasets, but are not competitive with Vision Transformers when given access to datasets on the web-scale. We challenge this belief by evaluating a performant…

While adversarial training has been extensively studied for ResNet architectures and low resolution datasets like CIFAR, much less is known for ImageNet. Given the recent debate about whether transformers are more robust than convnets, we…

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

Inception and the Resnet family of Convolutional Neural Network archi-tectures have broken records in the past few years, but recent state of the art models have also incurred very high computational cost in terms of training, inference and…

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…

Although the image recognition has been a research topic for many years, many researchers still have a keen interest in it[1]. In some papers[2][3][4], however, there is a tendency to compare models only on one or two datasets, either…

We show that Residual Networks (ResNet) is equivalent to boosting feature representation, without any modification to the underlying ResNet training algorithm. A regret bound based on Online Gradient Boosting theory is proved and suggests…

Unlocking large-scale low-bandwidth decentralized training has the potential to utilize otherwise untapped compute resources. In centralized settings, large-scale multi-node training is primarily enabled by data and pipeline parallelism,…

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for image recognition problems. Nevertheless, it is not trivial when utilizing a CNN for learning spatio-temporal video representation. A few studies have…

The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal three-dimensional (3D) kernels. Recently, the performance levels…

A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the…

Channel estimation is crucial in wireless communications. However, in many papers neural networks are frequently tested by training and testing on one example channel or similar channels. This is because data-driven methods often degrade on…

The machine learning community has witnessed a drastic change in the training pipeline, pivoted by those ''foundation models'' with unprecedented scales. However, the field of adversarial training is lagging behind, predominantly centered…

Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently…

The effectiveness of shortcut/skip-connection has been widely verified, which inspires massive explorations on neural architecture design. This work attempts to find an effective way to design new network architectures. It is discovered…

Network pruning is an effective method to reduce the computational expense of over-parameterized neural networks for deployment on low-resource systems. Recent state-of-the-art techniques for retraining pruned networks such as weight…