# Overcoming Language Bias in Remote Sensing Visual Question Answering via Adversarial Training

arXiv: https://arxiv.org/abs/2306.00483 · HTML: https://mlsanity.com/paper/2306.00483/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 1 Jun 2023.

## Builds on (most cited first, 10 of 10)

- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [RSVQA: Visual Question Answering for Remote Sensing Data](https://mlsanity.com/paper/2003.07333/) (2020)
- [EarthNets: Empowering AI in Earth Observation](https://mlsanity.com/paper/2210.04936/) (2022)
- [From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data](https://mlsanity.com/paper/2205.03147/) (2022)
- [Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder](https://mlsanity.com/paper/2007.06198/) (2020)
- [Change Detection Meets Visual Question Answering](https://mlsanity.com/paper/2112.06343/) (2021)
- [Multilingual Augmentation for Robust Visual Question Answering in Remote Sensing Images](https://mlsanity.com/paper/2304.03844/) (2023)
- [Language bias in Visual Question Answering: A Survey and Taxonomy](https://mlsanity.com/paper/2111.08531/) (2021)
- [GAMUS: A Geometry-aware Multi-modal Semantic Segmentation Benchmark for Remote Sensing Data](https://mlsanity.com/paper/2305.14914/) (2023)

## Built on by (most cited first, 1 of 1)

- [SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model](https://mlsanity.com/paper/2401.09712/) (2024)

## Abstract (arXiv)

The Visual Question Answering (VQA) system offers a user-friendly interface and enables human-computer interaction. However, VQA models commonly face the challenge of language bias, resulting from the learned superficial correlation between questions and answers. To address this issue, in this study, we present a novel framework to reduce the language bias of the VQA for remote sensing data (RSVQA). Specifically, we add an adversarial branch to the original VQA framework. Based on the adversarial branch, we introduce two regularizers to constrain the training process against language bias. Furthermore, to evaluate the performance in terms of language bias, we propose a new metric that combines standard accuracy with the performance drop when incorporating question and random image information. Experimental results demonstrate the effectiveness of our method. We believe that our method can shed light on future work for reducing language bias on the RSVQA task.