SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.09224 · ICCV · 2023

Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories

Fei Sha, Thomas Mensink, Vittorio Ferrari, Felipe Cadar, André Araujo, Arushi Goel, Jasper Uijlings, Lluis Castrejon, Howard Zhou, Prince Brâncoveanu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose Encyclopedic-VQA, a large scale visual question answering (VQA) dataset featuring visual questions about detailed properties of fine-grained categories and instances. It contains 221k unique question+answer pairs each matched with (up to) 5 images, resulting in a total of 1M VQA samples. Moreover, our dataset comes with a controlled knowledge base derived from Wikipedia, marking the evidence to support each answer. Empirically, we show that our dataset poses a hard challenge for large vision+language models as they perform poorly on our dataset: PaLI [12] is state-of-the-art on OK-VQA [35], yet it only achieves 13.0% accuracy on our dataset. Moreover, we experimentally show that progress on answering our encyclopedic questions can be achieved by augmenting large models with a mechanism that retrieves relevant information from the knowledge base. An oracle experiment with perfect retrieval achieves 87.0% accuracy on the singlehop portion of our dataset, and an automatic retrievalaugmented prototype yields 48.8%. We believe that our dataset 1 enables future research on retrieval-augmented vi-sion+language models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2306.09224")
get_code_for_paper("2306.09224")
have("2306.09224")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2306.09224.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2306.09224.svg)](https://syntology.ai/paper/2306.09224)

Connect an agent — have() is free.