525 datasets found

The dataset used in the paper is ImageNet-52P, a subset of ImageNet for object detection.

A variant of the CIFAR100 dataset, containing 100 fine-grained image classes aggregated into 20 distinct super-classes.

The COCO-stuff dataset contains images of people performing various activities, such as playing sports, riding bicycles, and more.

The Swin Transformer dataset is a dataset for visual transformer.

CelebA-HQ, ImageNet

CIFAR-10, CIFAR-100, SVHN, MNIST, KMNIST, FashionMNIST

The DenseNet dataset is a dataset for image recognition on handwritten digits composed of 60,000 training data and 10,000 test images.

The COCO detection track dataset is used for object detection tasks.

The So2Sat LCZ42 dataset is a benchmark dataset for global local climate zones classification from Sentinel-2 images.

BeeImage dataset

Bumble bee species image classification dataset

The dataset used in the paper is ISLVRC2012, a dataset for image classification.

The dataset used in the paper is MIT Places 365, a dataset for scene recognition.

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}...

The dataset used in the paper is ImageNet32x32, a down-sampled version of ImageNet.

The dataset used in the paper to evaluate the effectiveness of the Unlearnable Clusters (UCs) technique.

Fine-grained image classification, which aims to recognize subordinate level categories, has emerged as a popular research area in the computer vision community.

The dataset used in the paper is the VGG dataset, which is a collection of images used for training and testing VGG models.

The iNaturalist 2021-mini dataset contains images of animals from 200 species.

The CUB dataset is a large collection of images of birds, each image is a 299x299 RGB image, and there are 11,778 training images and 5,994 testing images.