14 datasets found

The Office-10 dataset is a more classic benchmark dataset from [17].

The ImageCLEF-DA1 dataset is also a benchmark dataset for domain adaptation, which contains 12 categories shared by three public datasets, Caltech- 256 (C), ImageNet ILSVRC 2012...

The Office-31 dataset is a standard benchmark for domain adaptation from [16], comprising 4,652 images and 31 categories collected from three distinct domains: Amazon (A), Webcam...

A dataset for the study of domain adaptation solutions, composed of synthetic and real videos from seven gesture classes, from both the ground and air perspectives.

The Office-Home dataset is a visual domain adaptation task, where the goal is to adapt a model trained in a source domain to a target domain with different distributions.

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 FMoW dataset aims to classify utility types from satellite images.

Real-world applications of machine learning models often confront data distribution shifts, where discrepancies exist between the training and test data distributions.

VisDA-2017 is a simulation-to-real dataset with two extremely distinct domains: Synthetic renderings of 3D models and Real collected from photo-realistic or real-image datasets.

The dataset used in the paper is a cross-domain dataset, consisting of six domains: Real, Painting, Sketch, Clipart, Infograph, and Quickdraw. Each domain contains 345 object...

The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and...

The MNIST dataset (Lecun et al., 1998), which consists of 60,000 gray-scale images of handwritten digits. Each image has an accompanying label in {0, 1,..., 9}, and is stored as...