Self-attention based transformer models have been dominating many comput...
Vision transformers (ViT) have recently attracted considerable attention...
We study the few-shot learning (FSL) problem, where a model learns to
re...
Deep neural network is an effective choice to automatically recognize hu...
Automatic lung lesions segmentation of chest CT scans is considered a pi...
The rapid rise of IoT and Big Data has facilitated copious data driven
a...
Network pruning has become the de facto tool to accelerate deep neural
n...
The choice of activation function in deep networks has a significant eff...
Recently, differentiable neural architecture search methods significantl...
In general, image restoration involves mapping from low quality images t...
Temporal action localization in untrimmed videos is an important but
dif...
Convolutional neural networks (CNNs) are inherently suffering from massi...
Kernel approximation methods have been popular techniques for scalable k...
Group convolution works well with many deep convolutional neural network...
Pattern recognition on big data can be challenging for kernel machines a...
With a rapidly increasing number of devices connected to the internet, b...