ALFred: An Active Learning Framework for Real-world Semi-supervised Anomaly Detection with Adaptive Thresholds

TL;DR

This paper presents ALFred, an active learning framework for real-world video anomaly detection that adapts thresholds dynamically using human-in-the-loop pseudo-labeling, improving detection accuracy in changing environments.

Contribution

The paper introduces a novel active learning approach with human-in-the-loop for adaptive thresholding in VAD, addressing challenges of environmental variability and domain shifts.

Findings

Achieves an EBI of 68.91 for Q3 in simulated real-world scenarios.

Effectively adapts to changing definitions of normal and anomalous behavior.

Enhances the practical applicability of VAD in dynamic environments.

Abstract

Video Anomaly Detection (VAD) can play a key role in spotting unusual activities in video footage. VAD is difficult to use in real-world settings due to the dynamic nature of human actions, environmental variations, and domain shifts. Traditional evaluation metrics often prove inadequate for such scenarios, as they rely on static assumptions and fall short of identifying a threshold that distinguishes normal from anomalous behavior in dynamic settings. To address this, we introduce an active learning framework tailored for VAD, designed for adapting to the ever-changing real-world conditions. Our approach leverages active learning to continuously select the most informative data points for labeling, thereby enhancing model adaptability. A critical innovation is the incorporation of a human-in-the-loop mechanism, which enables the identification of actual normal and anomalous instances from pseudo-labeling results generated by AI. This collected data allows the framework to define an adaptive threshold tailored to different environments, ensuring that the system remains effective as the definition of 'normal' shifts across various settings. Implemented within a lab-based framework that simulates real-world conditions, our approach allows rigorous testing and refinement of VAD algorithms with a new metric. Experimental results show that our method achieves an EBI (Error Balance Index) of 68.91 for Q3 in real-world simulated scenarios, demonstrating its practical effectiveness and significantly enhancing the applicability of VAD in dynamic environments.