# Exploring Weaknesses of VQA Models through Attribution Driven Insights

Source: [Exploring Weaknesses of VQA Models through Attribution Driven Insights](<https://www.sota2.com/research/paper/68fa67b41e209131cea17f36>)

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

Data updated: 2025-10-25T22:20:05.971Z

Authors: Shaunak Halbe

Published: 2020-06-11T17:30:07.000Z

## Abstract

Deep Neural Networks have been successfully used for the task of Visual Question Answering for the past few years owing to the availability of relevant large scale datasets. However these datasets are created in artificial settings and rarely reflect the real world scenario. Recent research effectively applies these VQA models for answering visual questions for the blind. Despite achieving high accuracy these models appear to be susceptible to variation in input questions.We analyze popular VQA models through the lens of attribution (input's influence on predictions) to gain valuable insights. Further, We use these insights to craft adversarial attacks which inflict significant damage to these systems with negligible change in meaning of the input questions. We believe this will enhance development of systems more robust to the possible variations in inputs when deployed to assist the visually impaired.

## 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/2006.06637>)

[PDF](<https://arxiv.org/pdf/2006.06637.pdf>)
