FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering

03/19/2023
by   Weizhe Lin, et al.
0

The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to answer. It has been observed that the original dataset is highly imbalanced and concentrated on a small portion of its associated knowledge graph. We introduce FVQA 2.0 which contains adversarial variants of test questions to address this imbalance. We show that systems trained with the original FVQA train sets can be vulnerable to adversarial samples and we demonstrate an augmentation scheme to reduce this vulnerability without human annotations.

READ FULL TEXT
research
06/17/2016

FVQA: Fact-based Visual Question Answering

Visual Question Answering (VQA) has attracted a lot of attention in both...
research
08/12/2022

Forecasting Question Answering over Temporal Knowledge Graphs

Question answering over temporal knowledge graphs (TKGQA) has recently f...
research
08/29/2023

KGConv, a Conversational Corpus grounded in Wikidata

We present KGConv, a large, conversational corpus of 71k conversations w...
research
04/08/2019

AQuA: An Adversarially Authored Question-Answer Dataset for Common Sense

Commonsense reasoning is a critical AI capability, but it is difficult t...
research
04/08/2019

CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense

Commonsense reasoning is a critical AI capability, but it is difficult t...
research
08/19/2019

Message Passing for Complex Question Answering over Knowledge Graphs

Question answering over knowledge graphs (KGQA) has evolved from simple ...
research
07/20/2023

Towards Ontologically Grounded and Language-Agnostic Knowledge Graphs

Knowledge graphs (KGs) have become the standard technology for the repre...

Please sign up or login with your details

Forgot password? Click here to reset