Zero-shot domain adaptation of anomalous samples for semi-supervised anomaly detection
This addresses domain adaptation for anomaly detection in practical scenarios where anomalous samples are scarce, but it is incremental as it builds on existing SSAD and domain adaptation techniques.
The paper tackles the problem of semi-supervised anomaly detection (SSAD) failing under domain shifts when no anomalous data is available for the target domain, proposing a method that achieves adaptation with a domain-adversarial network and weighted loss function.
Semi-supervised anomaly detection~(SSAD) is a task where normal data and a limited number of anomalous data are available for training. In practical situations, SSAD methods suffer adapting to domain shifts, since anomalous data are unlikely to be available for the target domain in the training phase. To solve this problem, we propose a domain adaptation method for SSAD where no anomalous data are available for the target domain. First, we introduce a domain-adversarial network to a variational auto-encoder-based SSAD model to obtain domain-invariant latent variables. Since the decoder cannot reconstruct the original data solely from domain-invariant latent variables, we conditioned the decoder on the domain label. To compensate for the missing anomalous data of the target domain, we introduce an importance sampling-based weighted loss function that approximates the ideal loss function. Experimental results indicate that the proposed method helps adapt SSAD models to the target domain when no anomalous data are available for the target domain.