18 datasets found

The dataset used in the paper is a collection of autonomous vehicle scenarios, where each scenario is represented as a 3x3 grid encoding. The scenarios are encoded using Pauli-X...

The Drawing Recognition dataset is used to recognize drawings.

Image Recognition FeedbackLog

The MNIST dataset is a collection of images of handwritten digits, with size n = 70,000 and D = 784.

Self-Attention Networks dataset is used for image recognition tasks.

Inception V2 is a deep neural network for image recognition. It uses a convolutional neural network (CNN) architecture and is trained on a large dataset of images.

The ResNet-50 and ResNet-101 are used as the backbone image feature extractor.

The dataset used in this paper is the CIFAR10 dataset, which contains 60,000 32x32 color images in 10 classes, with 6,000 images per class.

Google Landmark Recognition 2021 Competition dataset

A dataset of ImageNet images with subtle 3D perspective changes that can break ImageNet-trained classification networks.

A dataset of complex image data with a fixed, known distribution, generated using a computer graphics pipeline.

The Vehicle License Plate (VLP) dataset is a dataset for image recognition and image processing tasks.

The dataset used in the paper is LAION-2B, which is a large-scale image-text dataset. The authors fine-tune a pre-trained diffusion model with a subset of LAION-2B with 10k...

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...

The dataset used in this paper is a neural network, and the authors used it to test the performance of their lookahead pruning method.

An image is worth 16x16 words: Transformers for image recognition at scale.

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...

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...