CLEVR

CLEVR is a diagnostic dataset that tests a range of visual reasoning abilities. It contains minimal biases and has detailed annotations describing the kind of reasoning each question requires. We use this dataset to analyze a variety of modern visual reasoning systems, providing novel insights into their abilities and

Papers using CLEVR (4)

RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation2022 · 14 citesOn the Relationship Between Variational Inference and Auto-Associative Memory2022 · 1 citesAre Diffusion Models Vision-And-Language Reasoners?2023Investigating Object Compositionality in Generative Adversarial Networks2018