2020
DOI: 10.48550/arxiv.2006.09273
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Density of States Estimation for Out-of-Distribution Detection

Abstract: Perhaps surprisingly, recent studies have shown probabilistic model likelihoods have poor specificity for out-of-distribution (OOD) detection and often assign higher likelihoods to OOD data than in-distribution data. To ameliorate this issue we propose DoSE, the density of states estimator. Drawing on the statistical physics notion of "density of states," the DoSE decision rule avoids direct comparison of model probabilities, and instead utilizes the "probability of the model probability," or indeed the freque… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
12
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
6
2

Relationship

1
7

Authors

Journals

citations
Cited by 8 publications
(12 citation statements)
references
References 10 publications
0
12
0
Order By: Relevance
“…Bulusu et al, 2020, for a recent survey]. In particular, HCL detects task changes by measuring the typicality of the model's statistics, which is similar to recently proposed state-of-the-art OOD detection methods by Nalisnick et al [2019c] and Morningstar et al [2020]. In some of our experiments, we apply HCL to embeddings extracted by a deep neural network; develop a related method for OOD detection, where a flow-based generative model approximates the density of intermediate representations of the data.…”
Section: Related Workmentioning
confidence: 89%
See 2 more Smart Citations
“…Bulusu et al, 2020, for a recent survey]. In particular, HCL detects task changes by measuring the typicality of the model's statistics, which is similar to recently proposed state-of-the-art OOD detection methods by Nalisnick et al [2019c] and Morningstar et al [2020]. In some of our experiments, we apply HCL to embeddings extracted by a deep neural network; develop a related method for OOD detection, where a flow-based generative model approximates the density of intermediate representations of the data.…”
Section: Related Workmentioning
confidence: 89%
“…Similarly to prior work on anomaly detection [Nalisnick et al, 2019c] and[Morningstar et al, 2020], we detect task changes measuring the typicality of the HCL model's statistics. Following Morningstar et al [2020], we can use the following statistics on data batches B:…”
Section: Task Identificationmentioning
confidence: 99%
See 1 more Smart Citation
“…Other methods focus on the data distribution directly: Nalisnick et al (2019a) discovered that the density learned by generative models cannot distinguish between ID and OOD inputs. Various works study this observation identifying background statistic (Ren et al, 2019), excessive influence of input complexity (Serrà et al, 2020), and mismatch between the typical set and highdensity regions (Nalisnick et al, 2019b;Choi et al, 2019;Morningstar et al, 2020) as causes. In comparison to our work, these methods focus on flow-based and autoregressive density methods with tractable likelihood.…”
Section: Related Workmentioning
confidence: 99%
“…First note that, similarly to tabular data, semantic node features are less likely to suffer from the same flaws. Second, following previous works [14,15,46,68,97], GPN mitigates this issue by using density estimation on a latent space which is low-dimensional and task-specific. Nonetheless, we emphasize that GPN provides predictive uncertainty estimates which depends on the considered task i.e.…”
Section: Limitations and Impactmentioning
confidence: 99%