Computer Vision - Groups

ImageNet-50/100/200

The dataset used in the paper is not explicitly mentioned, but it is implied to be ImageNet-50/100/200 for ImageNet-50/100/200 classification.

Dataset
JSON

Occluded CIFAR

The dataset used in the paper is Occluded CIFAR.

Dataset
JSON

Cluttered MNIST and CIFAR-10

The dataset used in the paper is Cluttered MNIST and CIFAR-10.

Dataset
JSON

Counting Objects by Diﬀused Index

Counting objects is a fundamental but challenging problem. In this paper, we propose diﬀusion-based, geometry-free, and learning-free methodologies to count the number of...

Dataset
JSON

ImageNet-32

The ImageNet-32 dataset is a subset of the ImageNet dataset, containing 1,281,167 training samples and 50,000 test samples, distributed across 1,000 labels.

Dataset
JSON

DTU MVS Dataset

The DTU MVS dataset contains 49 images of physical objects in real environments.

Dataset
JSON

CIFAR10 and ImageNet

The dataset used in the paper to evaluate the alignment of deep neural networks with human perception.

Dataset
JSON

Fishyscapes

Fishyscapes: A benchmark for safe semantic segmentation in autonomous driving with annotations for pedestrian and vehicle detection.

Dataset
JSON

MUAD: Multiple Uncertainties for Autonomous Driving

MUAD: A synthetic dataset for autonomous driving with multiple uncertainties and annotations for semantic segmentation, depth estimation, object detection, and instance...

Dataset
JSON

Container: A General-Purpose Building Block for Multi-Head Context Aggregation

Convolutional neural networks (CNNs) are ubiquitous in computer vision, with a myriad of effective and efﬁcient variations. Recently, Transformers – originally introduced in...

Dataset
JSON

Mutant and LEGO Dataset

The Mutant and LEGO dataset is a dynamic scene dataset. It contains 90% images for training and 10% images for evaluation.

Dataset
JSON

Tanks and Temples Advanced (T&T) Dataset

The Tanks and Temples Advanced (T&T) dataset is a benchmark dataset for image-based 3D reconstruction. It contains 90% images for training and 10% images for evaluation.

Dataset
JSON

Visual Wake Words (VWW) dataset

The Visual Wake Words (VWW) dataset consists of high-resolution images that include visual cues to 'wake-up' AI-powered home assistant devices.

Dataset
JSON

HSViT: Horizontally Scalable Vision Transformer

This paper introduces a horizontally scalable vision transformer (HSViT) scheme with a novel image-level feature embedding. The design of HSViT preserves the inductive bias from...