# FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning

arXiv: https://arxiv.org/abs/2404.06653 · HTML: https://mlsanity.com/paper/2404.06653/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 9 Apr 2024.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [Revisiting Training Strategies and Generalization Performance in Deep Metric Learning](https://mlsanity.com/paper/2002.08473/) (2020)
- [RepMet: Representative-based metric learning for classification and one-shot object detection](https://mlsanity.com/paper/1806.04728/) (2018)
- [Attention-based Ensemble for Deep Metric Learning](https://mlsanity.com/paper/1804.00382/) (2018)
- [Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset](https://mlsanity.com/paper/2012.14036/) (2020)
- [Learning Intra-Batch Connections for Deep Metric Learning](https://mlsanity.com/paper/2102.07753/) (2021)
- [A comprehensive survey of research towards AI-enabled unmanned aerial systems in pre-, active-, and post-wildfire management](https://mlsanity.com/paper/2401.02456/) (2024)
- [Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss](https://mlsanity.com/paper/2008.04378/) (2020)
- [Deep Metric Learning by Online Soft Mining and Class-Aware Attention](https://mlsanity.com/paper/1811.01459/) (2018)
- [Wildfire Monitoring in Remote Areas using Autonomous Unmanned Aerial Vehicles](https://mlsanity.com/paper/1905.00492/) (2019)
- [Human Motion Analysis with Deep Metric Learning](https://mlsanity.com/paper/1807.11176/) (2018)
- [Attention-based Open RAN Slice Management using Deep Reinforcement Learning](https://mlsanity.com/paper/2306.09490/) (2023)
- [Thermal Image Calibration and Correction using Unpaired Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/2401.11582/) (2024)
- [Triplet Loss-less Center Loss Sampling Strategies in Facial Expression Recognition Scenarios](https://mlsanity.com/paper/2302.04108/) (2023)
- [Joint Path planning and Power Allocation of a Cellular-Connected UAV using Apprenticeship Learning via Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/2306.10071/) (2023)
- [PyroTrack: Belief-Based Deep Reinforcement Learning Path Planning for Aerial Wildfire Monitoring in Partially Observable Environments](https://mlsanity.com/paper/2403.11095/) (2024)

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

- [Seeing Heat with Color -- RGB-Only Wildfire Temperature Inference from SAM-Guided Multimodal Distillation using Radiometric Ground Truth](https://mlsanity.com/paper/2505.01638/) (2025)
- [PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics](https://mlsanity.com/paper/2512.17152/) (2025)

## Abstract (arXiv)

FlameFinder is a deep metric learning (DML) framework designed to accurately detect flames, even when obscured by smoke, using thermal images from firefighter drones during wildfire monitoring. Traditional RGB cameras struggle in such conditions, but thermal cameras can capture smoke-obscured flame features. However, they lack absolute thermal reference points, leading to false positives.To address this issue, FlameFinder utilizes paired thermal-RGB images for training. By learning latent flame features from smoke-free samples, the model becomes less biased towards relative thermal gradients. In testing, it identifies flames in smoky patches by analyzing their equivalent thermal-domain distribution. This method improves performance using both supervised and distance-based clustering metrics.The framework incorporates a flame segmentation method and a DML-aided detection framework. This includes utilizing center loss (CL), triplet center loss (TCL), and triplet cosine center loss (TCCL) to identify optimal cluster representatives for classification. However, the dominance of center loss over the other losses leads to the model missing features sensitive to them. To address this limitation, an attention mechanism is proposed. This mechanism allows for non-uniform feature contribution, amplifying the critical role of cosine and triplet loss in the DML framework. Additionally, it improves interpretability, class discrimination, and decreases intra-class variance. As a result, the proposed model surpasses the baseline by 4.4% in the FLAME2 dataset and 7% in the FLAME3 dataset for unobscured flame detection accuracy. Moreover, it demonstrates enhanced class separation in obscured scenarios compared to VGG19, ResNet18, and three backbone models tailored for flame detection.