660 datasets found

CIFAR-100 and ILSVRC-2012 datasets used for training and testing the Zero Activation Predictor (ZAP) model.

The dataset used in the paper is a synthetic MNIST dataset generated by forming barycenters constructed with weights sampled uniformly from ∆3.

Selective search is a method for object detection.

The dataset used in the paper is CIFAR-10, CIFAR-100 and Tiny-Imagenet datasets.

The dataset used in the paper is COATNet-7, a neural network for image classification.

The VisDA dataset is a large-scale dataset for unsupervised domain adaptation, which consists of 152,397 synthetic images and 55,388 real-world images from the real world.

The Office-Home dataset is a dataset for unsupervised domain adaptation, which consists of 15,500 images from 65 classes in 4 distinct domains: Artistic images (Ar), Clip-Art...

The Office-31 dataset is a widely-used dataset for UDA, which consists of 4652 images of 31 categories from three domains: DSLR (D), Amazon (A), and Webcam (W).

The dataset used in the paper is WRN-22-8.

notMNIST is a dataset of 60,000 28x28 grayscale images in 10 classes, with 6,000 images per class.

An active learning (AL) algorithm seeks to construct an effective classifier with a minimal number of labeled examples in a boot-strapping manner.

The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset is a large-scale image classification dataset. It contains over 14 million images from 21,841 categories.

LAION-10k is a subset of LAION [24], comprising 10,000 image-text pairs with each image having a resolution of 256x256 pixels.

The dataset used in this paper is a collection of images from the STL-10 dataset, preprocessed and used for training and evaluation of the proposed diffusion spectral entropy...

The dataset used in the paper is CIFAR100, ImageNet100, and ImageNet. CIFAR100 consists of 100 object classes and 60,000 images. ImageNet100 has 100 object classes and 60,000...

The dataset used in the experiment was the ImageNet ILSVRC2012 dataset [24]. It has 1,000 classes and about 1.2 million total images.

The OpenImagesV4 dataset is a large benchmark dataset for object detection and image classification. It contains 1.7 million images with 1,000 object classes.

A semi-natural image dataset (BAM dataset) for evaluating attribution methods, constructed by pasting object pixels from MSCOCO into scene images from MiniPlaces.

The proposed SPANet selectively gathers contextual information from the salient positions in the low level and stops the error drift between network layers.

The MIT-67 dataset is a small-scale image classification dataset, consisting of 67 images from 6 classes.