Images

NVD

Naturalistic Variation Object Dataset

Introduced in Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing2022

About this Dataset

Naturalistic Variation Object Dataset (NVD) is a large simulated dataset of 272k images of everyday objects with naturalistic variations such as object pose, scale, viewpoint, lighting and occlusions.

Source: Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing

Image Source: https://arxiv.org/pdf/2211.16499v1.pdf

Source: Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing

Dataset Variants

NVD

Papers1

Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing

This work presents Counterfactual Simulation Testing, a counterfactual framework that allows for a fair comparison of the robustness of recently released, state-of-the-art Convolutional Neural Networks and Vision Transformers, with respect to naturalistic variations.

Tasks

EDIT

Counterfactual Inference

Similar Datasets

MNIST

CelebA

JFT-300M

Statistics

Papers

1

Tasks

64

Introduced

2022

Modalities

Images