# Data augmentation to improve robustness of image captioning solutions

Source: [Data augmentation to improve robustness of image captioning solutions](<https://www.sota2.com/research/paper/68fa6a1e1e209131cea26125>)

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

Data updated: 2025-10-27T06:07:38.446Z

Authors: Shashank Bujimalla, Mahesh Subedar, Omesh Tickoo

Published: 2021-06-10T00:17:50.000Z

## Abstract

In this paper, we study the impact of motion blur, a common quality flaw in real world images, on a state-of-the-art two-stage image captioning solution, and notice a degradation in solution performance as blur intensity increases. We investigate techniques to improve the robustness of the solution to motion blur using training data augmentation at each or both stages of the solution, i.e., object detection and captioning, and observe improved results. In particular, augmenting both the stages reduces the CIDEr-D degradation for high motion blur intensity from 68.7 to 11.7 on MS COCO dataset, and from 22.4 to 6.8 on Vizwiz dataset.

## 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/2106.05437>)

[PDF](<https://arxiv.org/pdf/2106.05437.pdf>)