660 datasets found

VisDA-2017 is a simulation-to-real dataset with two extremely distinct domains: Synthetic renderings of 3D models and Real collected from photo-realistic or real-image datasets.

The MNIST and FashionMNIST datasets are used for image classification tasks.

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 COCO dataset is a large-scale dataset for object detection, semantic segmentation, and captioning. It contains 80 object categories and 1,000 image instances per category,...

The MNIST-SVHN-Text dataset is a multi-modal dataset consisting of images, text, and labels.

Data-free quantization through weight equalization and bias correction.

Quantization is a promising approach for reducing the inference time and memory footprint of neural networks. However, most existing quantization methods require access to the...

The dataset used in this paper is the ResNet50 dataset, a deep neural network trained on the ImageNet dataset.

The dataset used in the paper is ImageNet-Dogs15, a subset of ImageNet containing 15 dog breeds.

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

CUB-200 is a fine-grained image classification dataset containing high resolution images of 200 different bird species.

A synthetic image dataset generated with Stable Diffusion using the Wordnet taxonomy and the definitions of concepts it contains.

Tiny Images dataset is a large dataset of images, each with a small size.

Privacy-preserving image classification method that uses ViT and a block-wise encryption method

Large-scale vision-and-language models trained on curated and web-scrapped data have led to significant improvements over task-specific models when transferred to downstream...

The dataset used in the paper is not explicitly described, but it is mentioned that it is a large-scale captioned image dataset (LAION) used to train the Stable Diffusion model.

The dataset used in the paper is the ILSVRC2012 dataset, which contains images of size 224x224.

The ETH-Zurich dataset contains a collection of 1000 examples of images, each with a label indicating whether the image contains a dog or not.

DeepFashion2 is a large-scale fashion image benchmark with comprehensive tasks and annotations. It contains 491K images, each of which is richly labeled with style, scale,...

The dataset used in the paper is a cross-domain dataset, consisting of six domains: Real, Painting, Sketch, Clipart, Infograph, and Quickdraw. Each domain contains 345 object...