120 datasets found

A synthetic dataset containing occluded objects paired with their whole counterparts.

The dataset is used for training a neural network for computational 3D phase imaging of multiple-scattering samples.

The Gemini 720i Panel-Pipe dataset is a dataset containing sonar images of underwater objects, captured using a Tritech Gemini 720i FLS.

The Marine Debris Watertank dataset is a dataset containing sonar images of underwater objects, captured using an ARIS Explorer 3000 FLS.

The Marine Debris Turntable dataset is a dataset containing sonar images of underwater objects, captured using an ARIS Explorer 3000 FLS, with objects in a rotating platform,...

The Sprites dataset has 672 synthetically rendered animated characters (sprites). The dataset is split into a training set with 500, a validation set with 72, and a test set...

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

The dataset used for training a Convolutional Neural Network to predict a grasp quality score over all grasp poses, given a depth image of an object.

The dataset used in the experiment consists of 50 images equally distributed between five classes: aircraft, bird, bicycle, boat, and dog. Each class has 5 true positive images...

The dataset used in the paper is ShapeNet-13, a collection of 3D models of objects

The Stanford Online Products (SOP) dataset contains 120,053 product images covering 22,634 categories. The training set is composed of 59,551 images of the first 11,318...

Selective search is a method for object detection.

The dataset used in the paper is a set of images, and the authors used it to train and test their ladder network model.

The THINGS dataset is a large-scale object concept dataset.

The CIFAR-100 dataset consists of 100 classes of 32 × 32 RGB images with 60,000 training and 10,000 testing examples.

A dataset of 3D models, including chairs, tables, and other objects.

The dataset used in the study on scale and translation-invariance for novel objects in human vision.

The dataset used in the study on translation tolerance in human visual pattern recognition.

The dataset used in the study on translation tolerance following extreme displacements.

The dataset used in this paper is a large-scale dataset containing 800K+ annotated 3D mesh objects. The dataset is used for training and validation of the proposed ConsistNet...