-
miniImageNet, tieredImageNet, Caltech-USCD birds-200-2011
miniImageNet, tieredImageNet, Caltech-USCD birds-200-2011 -
Imagenette
The Imagenette dataset used in the paper for class density and dataset quality in high-dimensional, unstructured data. -
Tiny ImageNet Visual Recognition Challenge
The Tiny-ImageNet dataset is a subset of the ImageNet dataset. -
Similarity Transfer for Knowledge Distillation
The proposed method aims to utilize the similarity correlation between different instances. -
CIFAR-10, CIFAR-100, FashionMNIST, and SVHN datasets
The dataset used in the paper is a benchmark dataset for multi-class image classification: CIFAR-10, CIFAR-100, FashionMNIST, and SVHN. -
Custom Dataset for Fine-tuning Open-sourced Models
The dataset used in this paper is a custom dataset generated for fine-tuning open-sourced models. -
ImageNet, MS COCO, Cityscapes, and ADE20K
The dataset used for the experiments in the paper, which includes ImageNet, MS COCO, Cityscapes, and ADE20K datasets. -
RSNA 2019 Brain CT Hemorrhage Challenge dataset
The RSNA 2019 Brain CT Hemorrhage Challenge dataset is a dataset of CT scans of the brain used for hemorrhage detection and classification. -
Caltech-UCSD Birds (CUB) dataset
The Caltech-UCSD Birds (CUB) dataset is a fine-grained visual classification dataset containing 200 classes of birds. -
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}... -
Very Deep Convolutional Networks for Large-Scale Image Recognition
The dataset consists of 60,000 images of objects in 200 categories, with 300 images per category. -
MNIST and CIFAR-10
The MNIST dataset is a large dataset of handwritten digits, and the CIFAR-10 dataset is a dataset of images from 10 different classes. -
ImageNet, ADE20K, and COCO datasets
The dataset used for ImageNet recognition, ADE20K semantic segmentation, and COCO panoptic segmentation. -
Open Images Dataset V4
A dataset for image classification, object detection, and visual relationship detection. -
UltraMNIST
UltraMNIST is a synthetic dataset generated by making use of the MNIST digits. For constructing an image, 3-5 digits are sampled such that the total sum of digits is less than 10. -
Salient-Imagenet
The dataset used in the paper is a large-scale dataset Salient-Imagenet, which is based on Imagenet with pixel-level annotations of irrelevant (spurious) and relevant (core)...
