Cross-Domain Fire Detection Across Indoor and Outdoor Scenes.

Vision-based fire detection is highly sensitive to domain shifts between indoor and outdoor scenes, which often degrades the generalization of supervised models trained on a single domain. To study this problem, the Fire Detection Dataset is curated from multiple public sources as a large-scale benchmark for cross-domain fire and smoke recognition. Cross-domain deployment faces two main challenges: substantial appearance variations in fire and smoke, and highly diverse negative classes that can easily trigger false alarms. To address these issues, a tailored cross-domain framework is studied by combining adversarial alignment and discrepancy-based statistical alignment to learn more domain-invariant features and mitigate negative transfer. Experimental results show that domain adaptation substantially improves target-domain generalization over weak alignment baselines. In particular, Domain-Adversarial Neural Networks (DANN) achieve 89.44% accuracy on Indoor → Outdoor and 79.10% on Outdoor → Indoor, while Multi-Kernel Maximum Mean Discrepancy (MK-MMD) attains the best fire-class F1-score of 78.04% on Outdoor → Indoor. These results highlight the value of domain alignment for improving robust fire detection across heterogeneous deployment environments.