# Analysis of Deep Learning Architectures and Efficacy of Detecting Forest Fires

arXiv: https://arxiv.org/abs/2212.04030 · HTML: https://mlsanity.com/paper/2212.04030/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 8 Dec 2022.

## Builds on (most cited first, 9 of 9)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset](https://mlsanity.com/paper/2012.14036/) (2020)
- [BoWFire: Detection of Fire in Still Images by Integrating Pixel Color and Texture Analysis](https://mlsanity.com/paper/1506.03495/) (2015)
- [Is it enough to optimize CNN architectures on ImageNet?](https://mlsanity.com/paper/2103.09108/) (2021)

## Abstract (arXiv)

The aim of this research is to review the state of computer vision as applied to combatting forest fires. My motivation to research this topic comes from the urgency with which new participants and stakeholders require guidance in this field. One of these new stakeholder groups are practitioners of machine learning that lack domain expertise. Introducing these new entrants to domain specific datasets and methods is critical to supporting this aim as general computer vision datasets are insufficient to support specialized research initiatives. The overarching aim of the research is to introduce datasets and methods to make them more accessible to the community.