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

Source: [C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset](<https://www.sota2.com/research/paper/68fa634b1e209131ce9fdc6d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:37:15.413Z

Authors: Aishwarya Agrawal, Aniruddha Kembhavi, Dhruv Batra, Devi Parikh

Published: 2017-04-26T17:57:59.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1704.08243>)

[PDF](<https://arxiv.org/pdf/1704.08243.pdf>)