C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset

04/26/2017
by   Aishwarya Agrawal, et al.
0

Visual Question Answering (VQA) has received a lot of attention over the past couple of years. A number of deep learning models have been proposed for this task. However, it has been shown that these models are heavily driven by superficial correlations in the training data and lack compositionality -- the ability to answer questions about unseen compositions of seen concepts. This compositionality is desirable and central to intelligence. In this paper, we propose a new setting for Visual Question Answering where the test question-answer pairs are compositionally novel compared to training question-answer pairs. To facilitate developing models under this setting, we present a new compositional split of the VQA v1.0 dataset, which we call Compositional VQA (C-VQA). We analyze the distribution of questions and answers in the C-VQA splits. Finally, we evaluate several existing VQA models under this new setting and show that the performances of these models degrade by a significant amount compared to the original VQA setting.

READ FULL TEXT

page 2

page 5

page 6

research
12/01/2017

Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

A number of studies have found that today's Visual Question Answering (V...
research
05/17/2022

Gender and Racial Bias in Visual Question Answering Datasets

Vision-and-language tasks have increasingly drawn more attention as a me...
research
08/10/2022

Aesthetic Visual Question Answering of Photographs

Aesthetic assessment of images can be categorized into two main forms: n...
research
07/03/2023

Localized Questions in Medical Visual Question Answering

Visual Question Answering (VQA) models aim to answer natural language qu...
research
06/23/2016

Analyzing the Behavior of Visual Question Answering Models

Recently, a number of deep-learning based models have been proposed for ...
research
12/04/2017

Learning by Asking Questions

We introduce an interactive learning framework for the development and t...
research
06/19/2021

VQA-Aid: Visual Question Answering for Post-Disaster Damage Assessment and Analysis

Visual Question Answering system integrated with Unmanned Aerial Vehicle...

Please sign up or login with your details

Forgot password? Click here to reset