cs.CVNov 16, 2026

How to Explain your Unexplainable Video Anomaly Detector

Authors: Giacomom D'Amicantonio, Egor Bondarev

Organizations: Eindhoven University of Technology, Eindhoven, The Netherlands

Abstract

Weakly-supervised Video Anomaly Detection (VAD) models assign anomaly scores from high-dimensional features, and their predictions remain unexplained. Saliency maps show where a model looks but not what it relies on, and the descriptions produced by Vision-Language Models (VLMs) are generated by branches that the anomaly score never reads. To address this faithfulness gap, we propose Explain The Unexplainable (ETU), a classifier-agnostic framework that audits frozen VAD models through counterfactual interventions in their feature space. ETU maps video features to a discrete dependency graph of agents, actions and outcomes (Ar→Aa→AoA_r \to A_a \to A_o), regenerates the features by graph-conditioned diffusion with selected nodes of the graph masked, and measures the change in the score of a frozen detector; one set of interventions is applied unchanged to every detector. The generator is trained only to reconstruct the input features, so it cannot learn the contrast it is asked to measure, and we validate the audit with experiments that test every alternative explanation of its results, from the cost of regeneration to random deletions of matched size. On UCF-Crime features obtained from a CLIP encoder, we show that substituting the scene semantics results in the largest drop for most detectors, and that removing the outcome chain of the graph (ΔrelΔ_{rel}) changes the anomaly score of all six audited detectors far more than removing the same number of random nodes, even though the random deletion perturbs the features about as much. We show that this targeted behavior comes from the divergence objective of the graph embedding. Without it, the two interventions become indistinguishable, and with a divergence objective in the generator as well, the score change of the detector follows the displacement of the reconstruction rather than the semantics that were removed.

Figures & tables

Appendix figures & tables30 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection

    May 14, 2026Mitchell Piehl, Muchao YeMultimodal Anomaly DetectionInterpretable Anomaly Detection

  2. CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection

    May 22, 2026Hyeongmuk Lim, Youngbum HurInterpretable Anomaly DetectionVLM Reasoning