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 coincide. 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.
Ziyu Wang (Tsinghua University)
More from the Same Authors
2021 : Quasi-Bayesian Dual Instrumental Variable Regression »
2021 Poster: Scalable Quasi-Bayesian Inference for Instrumental Variable Regression »
Ziyu Wang · Yuhao Zhou · Tongzheng Ren · Jun Zhu
2020 Poster: Further Analysis of Outlier Detection with Deep Generative Models »
Ziyu Wang · Bin Dai · David P Wipf · Jun Zhu