131 datasets found

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen...

The dataset used in the paper is the Caltech 101 Dataset and the ILSVRC 2012 Dataset.

The dataset used in the paper is the iNaturalist 2018 dataset, which is a real-world large-scale imbalanced dataset.

The Pascal VOC dataset is a benchmark for object detection and instance segmentation.

The E-MNIST dataset is a large dataset of handwritten digits, each image is 28x28 pixels and consists of 47 classes (0-9 and letters).

The K-MNIST dataset is a large dataset of handwritten digits, each image is 28x28 pixels and consists of 10 classes (0-9).

CIFAR10-LT: a long-tailed version of the CIFAR-10 dataset, where the training images are randomly removed class-wise to follow a pre-defined imbalance ratio.

The dataset used in the paper for out-of-distribution detection via conditional distribution entropy with optimal transport.

The dataset used to test the trigger detection accuracy.

The dataset used to train the trigger detector, generated from a public dataset through data augmentation.

The dataset used in this paper is the MNIST, CIFAR10, and CIFAR100 datasets.

The dataset used in this paper for image annotation, consisting of 4,999 annotated images with a vocabulary of up to 200 keywords.

The ImageNet ILSVRC 2012 validation dataset is used to evaluate the proposed approach.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a combination of datasets from the scikit-learn library and the UCI machine...

A dataset of 26K corn seed images, classified into pure seeds and three other defective classes (broken, silkcut, and discolored).

The gisette dataset is a collection of 20,000 text documents, each containing a single sentence.

The NIPS2017 dataset is a collection of images used for adversarial attacks.

The dataset consists of 2,000 data points for digits 0 to 9.

A synthetic dataset of blobs in 2D space, with different distributions for P and Q.

The dataset used in the paper is MNIST Fashion and MNIST Handwritten digits.