-
CIFAR100 Super-class
A variant of the CIFAR100 dataset, containing 100 fine-grained image classes aggregated into 20 distinct super-classes. -
Scattering Networks for Hybrid Representation Learning
Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modeling images. -
DeepLIFT: Learning Important Features Through Propagating Activation Differences
DeepLIFT is a method for assigning feature importance that compares a neuron's activation to its'reference', where the reference is the activation that the neuron has when the... -
COCO-stuff dataset
The COCO-stuff dataset contains images of people performing various activities, such as playing sports, riding bicycles, and more. -
Imagenet ILSVRC-2012
The Imagenet ILSVRC-2012 dataset contains more than 1.2 million training images, 50,000 validation images, and 100,000 test images. -
CelebA-HQ, ImageNet
CelebA-HQ, ImageNet -
CIFAR-10, CIFAR-100, SVHN, MNIST, KMNIST, FashionMNIST
CIFAR-10, CIFAR-100, SVHN, MNIST, KMNIST, FashionMNIST -
ResNet-50 dataset
The dataset used in this paper is the ResNet-50 dataset. -
Visual Domain Adaptation
The MNIST, MNIST-M, Street View House Numbers (SVHN), Synthetic Digits (SYN DIGITS), CIFAR-10 and STL-10 datasets are used for visual domain adaptation experiments. -
Improving Unsupervised Domain Adaptation with Mixup Training
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. -
Naturalist
The Naturalist dataset is a dataset of images of animals. -
ImageNet-BrightnessVariation
A dataset related to brightness-variation images to understand their impact on deep learning models. -
So2Sat LCZ42
The So2Sat LCZ42 dataset is a benchmark dataset for global local climate zones classification from Sentinel-2 images. -
BeeImage Dataset
BeeImage dataset -
Bumble Bee Species Image Classification
Bumble bee species image classification dataset -
ISLVRC2012
The dataset used in the paper is ISLVRC2012, a dataset for image classification. -
ResNest: Split-attention networks
ResNest: Split-attention networks. -
Colored MNIST dataset
The dataset used in the paper is a binary classification task in a 300-dimensional space. The procedure for generating the training dataset is as follows: Each label y ∈ {−1, 1}...
