FPMT: Enhanced Semi-Supervised Model for Traffic Incident Detection
This addresses the resource-intensive challenge of labeling data for traffic incident detection, offering an incremental improvement in semi-supervised methods for this domain.
The paper tackled traffic incident detection by proposing FPMT, a semi-supervised learning model that uses data augmentation and probabilistic pseudo-mixing, achieving outstanding performance on four real datasets, especially with low label rates.
For traffic incident detection, the acquisition of data and labels is notably resource-intensive, rendering semi-supervised traffic incident detection both a formidable and consequential challenge. Thus, this paper focuses on traffic incident detection with a semi-supervised learning way. It proposes a semi-supervised learning model named FPMT within the framework of MixText. The data augmentation module introduces Generative Adversarial Networks to balance and expand the dataset. During the mix-up process in the hidden space, it employs a probabilistic pseudo-mixing mechanism to enhance regularization and elevate model precision. In terms of training strategy, it initiates with unsupervised training on all data, followed by supervised fine-tuning on a subset of labeled data, and ultimately completing the goal of semi-supervised training. Through empirical validation on four authentic datasets, our FPMT model exhibits outstanding performance across various metrics. Particularly noteworthy is its robust performance even in scenarios with low label rates.