FireMatch: A Semi-Supervised Video Fire Detection Network Based on Consistency and Distribution Alignment

TL;DR

FireMatch is a semi-supervised video fire detection network that combines consistency regularization, adversarial distribution alignment, and fairness loss to improve detection accuracy with limited labeled data.

Contribution

The paper introduces FireMatch, a novel semi-supervised fire detection model that leverages consistency regularization, data augmentation, and adversarial alignment to enhance performance with scarce labeled data.

Findings

Achieved 76.92% and 91.81% accuracy on two fire datasets.

Outperforms current state-of-the-art semi-supervised methods.

Effectively handles limited labeled data in fire detection.

Abstract

Deep learning techniques have greatly enhanced the performance of fire detection in videos. However, video-based fire detection models heavily rely on labeled data, and the process of data labeling is particularly costly and time-consuming, especially when dealing with videos. Considering the limited quantity of labeled video data, we propose a semi-supervised fire detection model called FireMatch, which is based on consistency regularization and adversarial distribution alignment. Specifically, we first combine consistency regularization with pseudo-label. For unlabeled data, we design video data augmentation to obtain corresponding weakly augmented and strongly augmented samples. The proposed model predicts weakly augmented samples and retains pseudo-label above a threshold, while training on strongly augmented samples to predict these pseudo-labels for learning more robust feature representations. Secondly, we generate video cross-set augmented samples by adversarial distribution alignment to expand the training data and alleviate the decline in classification performance caused by insufficient labeled data. Finally, we introduce a fairness loss to help the model produce diverse predictions for input samples, thereby addressing the issue of high confidence with the non-fire class in fire classification scenarios. The FireMatch achieved an accuracy of 76.92% and 91.81% on two real-world fire datasets, respectively. The experimental results demonstrate that the proposed method outperforms the current state-of-the-art semi-supervised classification methods.