SIAVC: Semi-Supervised Framework for Industrial Accident Video Classification

TL;DR

SIAVC is a semi-supervised learning framework that improves industrial accident video classification by using novel augmentation modules and high-confidence pseudo-labeling, achieving state-of-the-art accuracy on new and existing datasets.

Contribution

The paper introduces SIAVC, a semi-supervised framework with innovative augmentation modules and pseudo-labeling strategies, along with a new dataset ECA9 for industrial accident video analysis.

Findings

Achieves 88.76% accuracy on ECA9 dataset.

Achieves 89.13% accuracy on Fire Detection dataset.

Outperforms existing semi-supervised methods in industrial accident video classification.

Abstract

Semi-supervised learning suffers from the imbalance of labeled and unlabeled training data in the video surveillance scenario. In this paper, we propose a new semi-supervised learning method called SIAVC for industrial accident video classification. Specifically, we design a video augmentation module called the Super Augmentation Block (SAB). SAB adds Gaussian noise and randomly masks video frames according to historical loss on the unlabeled data for model optimization. Then, we propose a Video Cross-set Augmentation Module (VCAM) to generate diverse pseudo-label samples from the high-confidence unlabeled samples, which alleviates the mismatch of sampling experience and provides high-quality training data. Additionally, we construct a new industrial accident surveillance video dataset with frame-level annotation, namely ECA9, to evaluate our proposed method. Compared with the state-of-the-art semi-supervised learning based methods, SIAVC demonstrates outstanding video classification performance, achieving 88.76\% and 89.13\% accuracy on ECA9 and Fire Detection datasets, respectively. The source code and the constructed dataset ECA9 will be released in \url{https://github.com/AlchemyEmperor/SIAVC}.