525 datasets found

We explore the problem of selectively forgetting categories from trained CNN classification models in federated learning (FL).

Image bert pre-training with online tokenizer.

The MS COCO 2014 Dataset contains images of 91 object categories, which contains 82783 training images, 40504 validation images and 40775 testing images.

The SDI dataset is a collection of 8,000 images of defects in industrial products.

The Oxford Flower dataset is a collection of 2,000 images of flowers in 80 classes.

The CUB Bird dataset is a collection of 4,521 images of birds in 200 classes.

The dataset used in the paper is the ImageNet validation set, a subset of the ImageNet dataset.

The dataset used in the paper is the YFCC-100M dataset, a large-scale image dataset.

The dataset used in the paper for diffusion model detection, containing synthetic images and real images.

The dataset used in the paper is CIFAR-10 and Fashion-MNIST.

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...

The dataset used in this paper is the FashionMNIST dataset, which consists of 60,000 images of clothing items from 10 different classes.

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.

The ResMLP-S12 dataset is used for image classification tasks.

Computed Tomography (CT) dataset for contrast phase classification

Tiny-Imagenet is a dataset of 100,000 224x224 color images, each belonging to one of 200 classes.

The USPS dataset consists of 9298 images of handwritten digits 0-9 (10 classes) of 16x16 pixels in gray scale.

The Willow Object Class dataset comprises 304 images gathered from Caltech-256 (Griffin et al., 2007) and Pascal VOC 2007 (Everingham et al., 2007).

The dataset used in this paper is ImageNet and CIFAR-10 for image classification, and Cityscapes for semantic segmentation.

The ImageNet-32 dataset is a subset of the ImageNet dataset, containing 1,281,167 training samples and 50,000 test samples, distributed across 1,000 labels.