-
CirCNN: Accelerating and Compressing Deep Neural Networks using Block-Circula...
CirCNN is a neural network architecture that uses block-circulant matrices to reduce the number of parameters and computations. -
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
ShuffleNet is an extremely efficient convolutional neural network for mobile devices. -
Building Efficient Deep Neural Networks with Unitary Group Convolutions
Unitary group convolutions (UGConvs) are a building block for neural networks that combines a group convolution with unitary transforms in feature space. -
AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Imag...
The proposed framework for image classification tasks, using a hypersphere representation of deep features. -
Photorealistic text-to-image diffusion models with deep language understanding
The authors present a photorealistic text-to-image diffusion model with deep language understanding. -
Direct Differentiable Augmentation Search
Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and... -
DRAIN: A Deep Learning Approach to Rain Retrieval from GPM Passive Microwave ...
Rain retrieval algorithm DRAIN using deep learning techniques -
MNIST, CIFAR-10, CIFAR-100, Tiny-ImageNet, VGG-like
The dataset used in the paper is MNIST, CIFAR-10, CIFAR-100, Tiny-ImageNet, and VGG-like. -
Lightweight Vision Transformer for US Segmentation
Lightweight vision transformer for US segmentation. -
Sparse Resnet50 model
The dataset used in this paper is a sparse Resnet50 model, which is a variant of the Resnet50 model with 80% sparsity. -
Two-level Group Convolution
The proposed two-level group convolution is suitable for distributed memory computing and robust with respect to the large number of groups. -
ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Cla...
Deep convolutional neural networks have achieved remarkable success in computer vision. However, deep neural networks require large computing resources to achieve high... -
Visualizing MuZero Models
MuZero, a model-based reinforcement learning algorithm that uses a value equivalent dynamics model. -
Plug-and-Play Algorithm Convergence Analysis From The Standpoint of Stochasti...
The dataset used in the Plug-and-Play algorithm convergence analysis. -
DAFAR: Defending against Adversaries by Feedback-Autoencoder Reconstruction
Deep learning has shown impressive performance on challenging perceptual tasks and has been widely used in software to provide intelligent services. However, researchers found... -
MNIST and CIFAR-10 datasets
The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions. -
Deep neural networks for fast segmentation of 3d medical images
Deep neural networks for fast segmentation of 3d medical images -
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
Gaussian processes (GPs) are non-parametric, flexible models that work well in many tasks. Combining GPs with deep learning methods via deep kernel learning (DKL) is especially... -
Lebanese Road Pothole Detection Dataset
The dataset used for pothole detection using deep learning
