Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework

TL;DR

This paper introduces a unified contrastive learning framework for human action anomaly detection that works effectively with few normal samples, improving scalability and generalization across categories.

Contribution

The paper proposes a novel contrastive learning approach with a diffusion-based generative augmentation strategy for few-shot human action anomaly detection.

Findings

Achieves state-of-the-art results on HumanAct12 dataset.

Effective in both seen and unseen category scenarios.

Enhances training efficiency and model scalability.

Abstract

Human Action Anomaly Detection (HAAD) aims to identify anomalous actions given only normal action data during training. Existing methods typically follow a one-model-per-category paradigm, requiring separate training for each action category and a large number of normal samples. These constraints hinder scalability and limit applicability in real-world scenarios, where data is often scarce or novel categories frequently appear. To address these limitations, we propose a unified framework for HAAD that is compatible with few-shot scenarios. Our method constructs a category-agnostic representation space via contrastive learning, enabling AD by comparing test samples with a given small set of normal examples (referred to as the support set). To improve inter-category generalization and intra-category robustness, we introduce a generative motion augmentation strategy harnessing a diffusion-based foundation model for creating diverse and realistic training samples. Notably, to the best of our knowledge, our work is the first to introduce such a strategy specifically tailored to enhance contrastive learning for action AD. Extensive experiments on the HumanAct12 dataset demonstrate the state-of-the-art effectiveness of our approach under both seen and unseen category settings, regarding training efficiency and model scalability for few-shot HAAD.