716 datasets found

The Vision Reservoir (ViR) is a novel model for image classification, which treats the image as a sequence of pixel patches. The sequences are then processed by using a...

The dataset used in this work is a custom synthetic dataset generated using the liquid-dsp library, containing 600000 examples of each of 13.8 million examples, with SNRs...

The LabelMe dataset is a natural scene dataset used for testing the performance of the IBTM model on image classification tasks.

The Street View House Number (SVHN) dataset consists of 32x32 RGB images of house numbers captured from Google Street View.

Object proposal generation models: We study how a detection model trained on a small set of source classes can provide proposals that generalize to unseen object classes.

The MobileNetV3 dataset is a dataset for image classification.

A 1k classes classification task with 1.2M training examples and 50k validation examples. The examples are colour images of various sizes.

The Caltech 101 Silhouette dataset is a collection of images of silhouettes.

The dataset used in the paper is YFCC100M, a large-scale video dataset. The dataset is used for foreground and background patch extraction and object recognition tasks.

Office-Home, Office-31, and DomainNet are benchmark datasets for semi-supervised domain adaptation.

Food-101 dataset is a large-scale dataset for food image classification, with 101 classes and over 30,000 images.

Fine-Grained Visual Classification (FGVC) is an important computer vision prob-lem that involves small diversity within the different classes, and often requires expert...

Medical image analysis is a hot research topic because of its usefulness in different clinical applications, such as early disease diagnosis and treatment. Convolutional neural...

The dataset used for the Places365-Standard OOD detection task.

Texture classification is an important and challenging problem in many image processing applications.

The dataset used for the CIFAR-100 vs CIFAR-10 OOD detection task.

The dataset used in the paper is ImageNet-5, ImageNet-20, and ImageNet-100, which are subsets of the ImageNet dataset.

A dataset of potato pests images for identification and classification.

The dataset used in this paper is a ResNet50 model, which is a convolutional neural network. The model is used to evaluate the effects of quantization on the compute...

The proposed method uses the MNIST, CIFAR10, and Dog and Cat datasets for experiments.