-
Oxford Flower
The Oxford Flower dataset is a collection of 2,000 images of flowers in 80 classes. -
ImageNet Validation Set
The dataset used in the paper is the ImageNet validation set, a subset of the ImageNet dataset. -
ImageNet-1K, Food-101, Birds, and Dogs datasets
The dataset used for image classification tasks, including ImageNet-1K, Food-101, Birds, and Dogs. -
Places dataset
The Places dataset is a large-scale dataset for scene recognition, containing 1 million images from 365 categories. -
CIFAR-10 and Fashion-MNIST
The dataset used in the paper is CIFAR-10 and Fashion-MNIST. -
Stanford Cars dataset
The Stanford Cars dataset is a dataset of images of cars, with 196 categories and approximately 16,000 images. The authors created a synthetic dataset by adding occlusions of... -
FashionMNIST dataset
The dataset used in this paper is the FashionMNIST dataset, which consists of 60,000 images of clothing items from 10 different classes. -
Sub-ImageNet dataset
Sub-ImageNet dataset consists of 60,000 training and 10,000 testing samples. -
CIFAR10 dataset
The dataset used in this paper is the CIFAR10 dataset, which contains 60,000 32x32 color images in 10 classes, with 6,000 images per class. -
MNIST and SVHN datasets
MNIST dataset consists of 60,000 training and 10,000 testing samples, while SVHN consists of 73,257 training and 26,032 testing digital images. -
ResMLP-S12
The ResMLP-S12 dataset is used for image classification tasks. -
Contrast Enhanced CT Phase Classification
Computed Tomography (CT) dataset for contrast phase classification -
Diffusion Denoised Smoothing
Diffusion Denoised Smoothing (DDS) requires no new technical ideas on top of what was introduced in the section above. -
Tiny-Imagenet
Tiny-Imagenet is a dataset of 100,000 224x224 color images, each belonging to one of 200 classes. -
LC25000 Lung and Colon Histopathological Image Dataset
The dataset is used for classification of histopathology images of lung cancer using Convolutional Neural Network (CNN). -
Inter-Instance Similarity Modeling for Contrastive Learning
The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich... -
USPS dataset
The USPS dataset consists of 9298 images of handwritten digits 0-9 (10 classes) of 16x16 pixels in gray scale. -
Multi-label Transformer
The proposed Multi-label Transformer architecture is designed for multi-label image classification, combining pixel attention and cross-window attention to better excavate the...