-
ImageNet-2012 and fine-tuning on other datasets
The dataset used for ImageNet-2012 and fine-tuning on other datasets. -
ImageNet-2012 and multilingual neural machine translation
The dataset used for ImageNet-2012 and multilingual neural machine translation. -
Dogs vs. Cats
The dataset used in the paper is Dogs vs. Cats, a binary classification dataset containing 3,000 dog and cat images. -
Simple CNAPS Dataset
The dataset is used for few-shot visual classification. It contains images of people wearing masks, not wearing masks, and wearing masks incorrectly. -
Face Mask Detection and Classification Dataset
The dataset is used for face mask detection and classification. It contains images of people wearing masks, not wearing masks, and wearing masks incorrectly. -
ImageCLEF-DA
The ImageCLEF-DA dataset is a benchmark dataset for ImageCLEF 2014 domain adaptation challenges, which contains 12 categories shared by three domains: Caltech-256 (C), ImageNet... -
UCF-101, ERA, and BAR datasets
This paper uses the UCF-101, Event Recognition in Aerial videos (ERA), and Biased Action Recognition (BAR) datasets for image classification tasks. -
CIFAR-100-C
The dataset used in the paper is the CIFAR-100-C dataset, which applies common corruptions such as changes in contrast or blurring to images from CIFAR-100. -
The CIFAR-10 Dataset
The CIFAR-10 dataset is a popular benchmark for image classification tasks. -
CIFAR-10, CIFAR-100
CIFAR-10 and CIFAR-100 are standard vision datasets with 50,000 training images across 10 and 100 classes, respectively. -
MNIST and Fashion MNIST
The dataset used for MNIST and Fashion MNIST binary classification tasks -
DeepFace: A Large-Scale Face Recognition Dataset
The DeepFace dataset is a large-scale face recognition dataset containing over 2 million images of faces. -
WikiArt: A Large-Scale Dataset of Artworks
The WikiArt dataset is a large-scale dataset of artworks, containing over 1 million images of paintings. -
VGGFace2: A Large-Scale Face Recognition Dataset
The VGGFace2 dataset is a large-scale face recognition dataset containing over 2 million images of faces. -
Federated Unlearning via Class-Discriminative Pruning
We explore the problem of selectively forgetting categories from trained CNN classification models in federated learning (FL). -
CAE v2: Context Autoencoder with CLIP Target
Masked image modeling (MIM) learns visual representation by masking and reconstructing image patches. Applying the reconstruction supervision on the CLIP representation has been... -
Microsoft COCO Dataset
The MS COCO 2014 Dataset contains images of 91 object categories, which contains 82783 training images, 40504 validation images and 40775 testing images. -
No Token Left Behind: Explainability-Aided Image Classification and Generation
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the ImageNet, ImageNetV2, ImageNet-Sketch, ImageNet-A, and Imagenet-R datasets.