-
Deep Image: Scaling up image recognition
Deep Image: Scaling up image recognition -
Batch Normalization: Accelerating Deep Network Training by Reducing Internal ...
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. -
ATCN: Agile Temporal Convolutional Network
This paper presents a scalable deep learning model called Agile Temporal Convolutional Network (ATCN) for high-accurate fast classification and time series prediction in... -
Skin Lesion Analysis Towards Melanoma Detection
Skin Lesion Analysis dataset for melanoma detection -
DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Seg...
A dataset for pancreas segmentation. -
URHI dataset
The dataset used for testing the proposed T-Net and Stack T-Net for single image dehazing. -
SOTS dataset
The dataset used for training and testing the proposed T-Net and Stack T-Net for single image dehazing. -
CNN Models
The dataset used in this paper is a large variety of popular CNN models, such as straight-forward, complicated-connected, and grouped architectures. -
Street View House Numbers (SVHN)
The Street View House Numbers (SVHN) dataset used consist of 32x32 10,000 labelled image pool, 30,000 unlabelled pool and 26,032 testing pool. -
Residual Networks
Residual Networks (ResNet) is composed of stacked entities referred to as residual blocks. A Residual Block of ResNet contains a module and an identity loop. -
PoseAction: Action Recognition for Patients in the Ward using Deep Learning A...
Real-time intelligent detection and prediction of subjects' behavior particularly their movements or actions is critical in the ward. -
Im2win: An Efficient Convolution Paradigm on GPU
Convolutional neural network (CNN) is an important network model widely used in computer vision, image processing, and scientific computing. CNN consists of an input layer, an... -
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
A comprehensive robustness benchmark for Document Layout Analysis (DLA) models, including 450K document images from 3 datasets. -
Kodak, Tecnick, and CLIC 2022
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used Kodak, Tecnick, and CLIC 2022 as their test sets. -
Flicker2W and LIU4K
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used Flicker2W and LIU4K as their training sets. -
ActualMed COVID-19 Chest X-ray Dataset Initiative
The ActualMed COVID-19 Chest X-ray Dataset Initiative is a collection of 13,975 CXR images of around 13,870 infected patients. -
COVID-19 Chest X-Ray Dataset Initiative
The COVID-19 Chest X-Ray Dataset Initiative is a collection of 13,975 CXR images of around 13,870 infected patients. -
COVID-19 Image Data Collection
The dataset of chest x-rays used in this paper come from COVID-19 image data collection from Joseph Paul Cohen and Paul Morrison and Lan Dao. This dataset contains x-rays of... -
COVID-19 image data collection and Covid-Net
The dataset used to train the proposed model is a combination of two open-source datasets called COVID-19 image data collection and Covid-Net.