15 datasets found

Groups: Computer Vision Organizations: No Organization

Filter Results

  • Stanford 3D Scanning Repository

    The dataset used in the paper is not explicitly described, but it is mentioned that the authors tested their model on various signal reconstruction tasks: 1D sinusoidal...

  • Open Images Dataset

    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...

  • THINGS: A database of 1,854 object concepts and more than 26,000 naturalistic...

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

  • Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of F...

    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...

  • CIFAR-10, CIFAR-100

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

  • Training Convolutional Networks with Web Images

    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...

  • Sketchy

    Sketchy is a large collection of sketch-photo pairs. The dataset consists of images from 125 different classes, with 100 photos each.

  • PASCAL VOC 2007

    Multi-label image recognition is a practical and challenging task compared to single-label image classification.

  • Caltech-UCSD Birds 200

    The Caltech-256 object category dataset is used for the feature extraction step, and the Omniglot dataset is used for the evaluation.

  • Shapenet

    Shapenet is a large-scale synthesis 3D object dataset, where we follow [9] to use the official test splits of chair, car, and motorbike categories for evaluation since they...

  • ScanObjectNN

    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...

  • Objaverse

    The Objaverse dataset contains around 800k 3D objects. After adopting simple filter leveraging CLIP [27] to remove the objects whose rendered images are not relevant to its...

  • LSUN

    The dataset used for training and validation of the proposed approach to combine semantic segmentation and dense outlier detection.

  • ImageNet Large Scale Visual Recognition Challenge

    A benchmark for low-shot recognition was proposed by Hariharan & Girshick (2017) and consists of a representation learning phase without access to the low-shot classes and a...

  • ModelNet40

    Point cloud registration is a crucial problem in computer vision and robotics. Existing methods either rely on matching local geometric features, which are sensitive to the pose...