Consistency-based Self-supervised Learning for Temporal Anomaly Localization

TL;DR

This paper introduces a consistency-based self-supervised learning approach for weakly supervised video anomaly localization, improving detection performance by enforcing score alignment across video augmentations.

Contribution

It proposes a novel self-supervised regularization method that enhances weakly supervised anomaly detection by enforcing consistency across augmented video views.

Findings

Improved performance on XD-Violence dataset.

Enforcing augmentation consistency enhances anomaly localization.

Method outperforms existing regularization approaches.

Abstract

This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training. In particular, we deal with the localization of anomalous activities within the video stream: this is a very challenging scenario, as training examples come only with video-level annotations (and not frame-level). Several recent works have proposed various regularization terms to address it i.e. by enforcing sparsity and smoothness constraints over the weakly-learned frame-level anomaly scores. In this work, we get inspired by recent advances within the field of self-supervised learning and ask the model to yield the same scores for different augmentations of the same video sequence. We show that enforcing such an alignment improves the performance of the model on XD-Violence.