Further Analysis of Outlier Detection with Deep Generative Models
This work addresses a counter-intuitive problem in outlier detection for researchers and practitioners using DGMs, offering incremental insights into evaluation practices.
The paper investigates why deep generative models (DGMs) often assign higher likelihood to outliers, proposing an explanation based on the mismatch between a model's typical set and high-density region, and introduces a novel outlier test that shows existing likelihood-based tests may not indicate model miscalibration.
The recent, counter-intuitive discovery that deep generative models (DGMs) can frequently assign a higher likelihood to outliers has implications for both outlier detection applications as well as our overall understanding of generative modeling. In this work, we present a possible explanation for this phenomenon, starting from the observation that a model's typical set and high-density region may not conincide. From this vantage point we propose a novel outlier test, the empirical success of which suggests that the failure of existing likelihood-based outlier tests does not necessarily imply that the corresponding generative model is uncalibrated. We also conduct additional experiments to help disentangle the impact of low-level texture versus high-level semantics in differentiating outliers. In aggregate, these results suggest that modifications to the standard evaluation practices and benchmarks commonly applied in the literature are needed.