A Causal Inference Look at Unsupervised Video Anomaly Detection


  • Xiangru Lin Sun Yat-sen University The University of Hong Kong
  • Yuyang Chen Sun Yat-sen University
  • Guanbin Li Sun Yat-sen University
  • Yizhou Yu The University of Hong Kong




Computer Vision (CV)


Unsupervised video anomaly detection, a task that requires no labeled normal/abnormal training data in any form, is challenging yet of great importance to both industrial applications and academic research. Existing methods typically follow an iterative pseudo label generation process. However, they lack a principled analysis of the impact of such pseudo label generation on training. Furthermore, the long-range temporal dependencies also has been overlooked, which is unreasonable since the definition of an abnormal event depends on the long-range temporal context. To this end, first, we propose a causal graph to analyze the confounding effect of the pseudo label generation process. Then, we introduce a simple yet effective causal inference based framework to disentangle the noisy pseudo label's impact. Finally, we perform counterfactual based model ensemble that blends long-range temporal context with local image context in inference to make final anomaly detection. Extensive experiments on six standard benchmark datasets show that our proposed method significantly outperforms previous state-of-the-art methods, demonstrating our framework's effectiveness.




How to Cite

Lin, X., Chen, Y., Li, G., & Yu, Y. (2022). A Causal Inference Look at Unsupervised Video Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 36(2), 1620-1629. https://doi.org/10.1609/aaai.v36i2.20053



AAAI Technical Track on Computer Vision II