284 datasets found

A dataset for histopathological image analysis

Improving image classification with location context.

The YFCC100M-GEO100 dataset contains 100,000 images with 100,000 geotags.

Benchmarking representation learning for natural world image collections.

Fine-grained image classification is a challenging computer vision task where various species share similar visual appearances, resulting in misclassification if merely based on...

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 CMU faces dataset contains 624 images of 20 persons with different poses and expressions, with and without sunglasses.

The dataset used in the paper for representation learning through latent canonicalizations.

Two public leaf datasets are used in this experiment. The training and testing sets are split with a ratio of 1:1 for model evaluation. The CottonCultivar dataset contains 80...

MIT Places dataset, a dataset of images of places.

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

Thyroid Nodule Classification Dataset (TNCD) is a benchmark for thyroid nodule diagnosis, containing 3493 ultrasound images taken from 2421 patients.

VGG16-BN dataset for image classification

The dataset used in this paper is CIFAR-10 and GIST1M.

A dataset of 10 simple object classes (pineapple, soccer, basketball, etc.) with white backgrounds.

The dataset used for training and testing the conditional generative adversarial networks for pattern recognition.

The MARCO dataset contains 493,214 scored images from five institutions, with images collected from imagers made from two different manufacturers and in-house imaging equipment.

MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification

The SLICE dataset contains images of slices of cheese.

Agricultural image dataset used to evaluate the proposed HaST-CW model.