# Visual Question Answering in Remote Sensing with Cross-Attention and Multimodal Information Bottleneck

arXiv: https://arxiv.org/abs/2306.14264 · HTML: https://mlsanity.com/paper/2306.14264/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 25 Jun 2023.

## Builds on (most cited first, 5 of 5)

- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [RSVQA: Visual Question Answering for Remote Sensing Data](https://mlsanity.com/paper/2003.07333/) (2020)
- [Learning Robust Representations via Multi-View Information Bottleneck](https://mlsanity.com/paper/2002.07017/) (2020)
- [Wider or Deeper: Revisiting the ResNet Model for Visual Recognition](https://mlsanity.com/paper/1611.10080/) (2016)

## Built on by (most cited first, 2 of 2)

- [GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing](https://mlsanity.com/paper/2601.17089/) (2026)
- [Hyperspectral Image Analysis in Single-Modal and Multimodal setting using Deep Learning Techniques](https://mlsanity.com/paper/2403.01546/) (2024)

## Abstract (arXiv)

In this research, we deal with the problem of visual question answering (VQA) in remote sensing. While remotely sensed images contain information significant for the task of identification and object detection, they pose a great challenge in their processing because of high dimensionality, volume and redundancy. Furthermore, processing image information jointly with language features adds additional constraints, such as mapping the corresponding image and language features. To handle this problem, we propose a cross attention based approach combined with information maximization. The CNN-LSTM based cross-attention highlights the information in the image and language modalities and establishes a connection between the two, while information maximization learns a low dimensional bottleneck layer, that has all the relevant information required to carry out the VQA task. We evaluate our method on two VQA remote sensing datasets of different resolutions. For the high resolution dataset, we achieve an overall accuracy of 79.11% and 73.87% for the two test sets while for the low resolution dataset, we achieve an overall accuracy of 85.98%.