120 datasets found

The Caltech-UCSD Birds-200-2011 Dataset consists of 11,169 bird images from 200 categories and each category has 60 images averagely.

The dataset used in this paper for 3D point cloud classification and adversarial example generation.

Object recognition is arguably the most important problem at the heart of computer vision. Recently, Barbu et al. introduced a dataset called ObjectNet which includes objects in...

Object recognition is arguably the most important problem at the heart of computer vision. Recently, Barbu et al. introduced a dataset called ObjectNet which includes objects in...

Object recognition is arguably the most important problem at the heart of computer vision. Recently, Barbu et al. introduced a dataset called ObjectNet which includes objects in...

A dataset of 101 images of silhouettes.

Zhou et al. (2023) - Sparsefusion

Common Objects in 3D (CO3Dv2)

A neuromorphic vision sensing (NVS) device represents visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene...

The dataset used in the paper Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects. The dataset consists of 30 unique 3D object models...

Coil20 is an object dataset consisting of 20 different object categories. 72 images per object are captured at different viewing angles with a total of 1440 images.

CIFAR-10 and CIFAR-100 are standard vision datasets with 50,000 training images across 10 and 100 classes, respectively.

iCubWorld Transformations (iCWT): a dataset for object recognition and manipulation

The Places dataset is a large-scale dataset for scene recognition, containing 1 million images from 365 categories.

Recognizing person in UAV images faces two main challenges: significant size difference and uncertain rotation variations.

The dataset used in the paper is dsprites: Disentangle-ment testing sprites dataset, which consists of 26,000 naturalistic object images.

The Stanford Cars dataset is a dataset of images of cars, with 196 categories and approximately 16,000 images. The authors created a synthetic dataset by adding occlusions of...

This dataset is used to train a Convolutional Neural Network (CNN) to classify objects from web images. The dataset is created by downloading images from the web using a query...

LINEMOD dataset is a widely used instance-level 6D object pose estimation dataset which consists of 13 different objects with significant shape variation.

The Willow Object Class dataset comprises 304 images gathered from Caltech-256 (Griffin et al., 2007) and Pascal VOC 2007 (Everingham et al., 2007).