-
CIFAR-100 Dataset
The CIFAR-100 dataset consists of 100 classes of 32 × 32 RGB images with 60,000 training and 10,000 testing examples. -
mini-ImageNet
The mini-ImageNet dataset is a subset of the ImageNet dataset, containing 60,000 images from 100 classes. -
MNIST Images
The dataset used in this paper is a collection of MNIST images. -
Background CIFAR-10
The Background CIFAR-10 dataset is a subset of the CIFAR-10 dataset with images of objects from 10 different classes on a white background. -
Background MNIST
The Background MNIST dataset is a subset of the MNIST dataset with images of handwritten digits on a white background. -
Waterbirds
Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers... -
CIFAR100-20
Self-supervised learning for small-scale datasets based on contrastive loss between multiple views of the data -
iNaturalist and ImageNet datasets
The dataset used for evaluating the Variable Length Embeddings (VLE) model, consisting of a mix of the iNaturalist and ImageNet datasets. -
CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet
The dataset used in the paper is a de-noising diffusion probabilistic model (DDPM) trained on CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet. -
FashionMNIST, CIFAR10, CIFAR100, and STL10
The dataset used in the paper is a collection of images from FashionMNIST, CIFAR10, CIFAR100, and STL10 datasets. -
Breast Cancer
A neural network with single-hidden layer of 64 hidden units and ReLU activations. A prior precision of ε = 1, a minibatch size of 128 and 16 Monte-Carlo samples are used for... -
PASCAL VOC Dataset
The PASCAL VOC dataset contains 20 classes, including person, animal, vehicle, and indoor, with 9,963 images containing 24,640 annotated objects. -
ImageNet-20 and ImageNet-100
The ImageNet-20 and ImageNet-100 datasets are used for zero-shot image classification tasks. -
Learning Interpretable Queries for Explainable Image Classification with Info...
Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating... -
Subsampled CIFAR10 and CIFAR100
The dataset used in the paper is a modified version of CIFAR10 and CIFAR100 datasets, subsampled to create irregularly scattered nodes for each image. -
Masked Classes Dataset
The masked classes dataset is a subset of the ImageNet dataset, where some class labels are masked. -
Binned Classes Dataset
The binned classes dataset is a subset of the ImageNet dataset, divided into bins based on class labels. -
ImageNet-1K and ImageNet-22K
The dataset used in the paper is the ImageNet-1K and ImageNet-22K datasets.
