-
CIFAR-10, CIFAR-100, and SVHN datasets
The dataset used in the paper is the CIFAR-10 and CIFAR-100 datasets, and the SVHN dataset. -
Masked Autoencoders Are Scalable Vision Learners
Masked autoencoders are scalable vision learners -
Masked convolution meets masked autoencoders
Masked convolution meets masked autoencoders -
Autoencoders with Intrinsic Dimension Constraints
Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representations -
DCASE 2019
The dataset used for acoustic scene classification, sound event detection and image classification tasks. -
CUB Birds 200-2011
A dataset of 11,788 images of birds, each annotated with 36 attributes. -
Classification Accuracy Score
Classification accuracy score (CAS) is a better proxy than FID and IS for performance of downstream training on generated data. -
Synthetic Data from Diffusion Models Improves ImageNet Classification
Large-scale text-to-image diffusion models can be fine-tuned to produce class-conditional models with SOTA FID and Inception Score on ImageNet. -
Udacity Dataset
The Udacity dataset has images recorded while driving on highways and residential roads (with and without lane markings) in clear weather during daytime. -
LSUN Dataset
The LSUN dataset is a collection of images of scenes from the SUN dataset. -
CIFAR-10, CIFAR-100, and ILSVRC-12
The dataset used in the paper is CIFAR-10 and CIFAR-100, and ILSVRC-12. -
ImageNet-1k and ImageNet-100
The dataset used in the paper is ImageNet-1k and ImageNet-100, which are large-scale image classification datasets. -
ImageNet trained PyTorch models under various simple image transformations
ImageNet trained PyTorch models are evaluated under various simple image transformations. -
Oxford Flowers
The dataset used in the paper is a collection of trained networks and their corresponding datasets. -
DualConv: Dual Convolutional Kernels for Lightweight Deep Neural Networks
The proposed DualConv is used to replace the standard convolution in VGG-16 and ResNet-50 to perform image classification experiments on CIFAR-10, CIFAR-100, and ImageNet datasets. -
MNIST, CIFAR10, and UDIS-D datasets
The MNIST and CIFAR10 datasets are used for image classification, while the UDIS-D dataset is used for image reconstruction.
