Abstract:

Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at least few task-relevant target domain training data are available for adaptation from the source to the target domain. However, this requires laborious model- tuning by the end-user who may prefer to have a system that works "out-of-the-box." To address such practical scenarios, we identify a novel target domain (inference-time) VAD task where no target domain training data are available. To this end, we propose a new 'Zero-shot Cross-domain Video Anomaly Detection (zxVAD)' framework that includes a future-frame prediction generative model setup. Different from prior future- frame prediction models, our model uses a novel Normalcy Classifier module to learn the features of normal event videos by learning how such features are different "relatively" to features in pseudo-abnormal examples. A novel Untrained Convolu- tional Neural Network based Anomaly Synthesis module crafts these pseudo-abnormal examples by adding foreign objects in normal video frames with no extra training cost. With our novel relative normalcy feature learning strategy, zxVAD general- izes and learns to distinguish between normal and abnormal frames in a new target domain without adaptation during inference. Through evaluations on common datasets, we show that zxVAD outperformsthestate-of-the-art(SOTA),regardless of whether task-relevant (i.e., VAD) source training data are avail- able or not. Lastly, zxVAD also beats the SOTA methods in inference-time efficiency metrics including the model size, total parameters, GPU energy consumption, and GMACs.