Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
This addresses a critical reliability issue for users of VAEs in applications like anomaly detection, though it is incremental as it builds on prior OOD detection methods.
The paper tackles the problem of out-of-distribution (OOD) detection in Variational Auto-encoders (VAEs), where existing methods often fail, and proposes Likelihood Regret as an efficient OOD score, achieving the best overall performance in benchmarks.
Deep probabilistic generative models enable modeling the likelihoods of very high dimensional data. An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood. However, some recent studies show that probabilistic generative models can, in some cases, assign higher likelihoods on certain types of OOD samples, making the OOD detection rules based on likelihood threshold problematic. To address this issue, several OOD detection methods have been proposed for deep generative models. In this paper, we make the observation that many of these methods fail when applied to generative models based on Variational Auto-encoders (VAE). As an alternative, we propose Likelihood Regret, an efficient OOD score for VAEs. We benchmark our proposed method over existing approaches, and empirical results suggest that our method obtains the best overall OOD detection performances when applied to VAEs.