Predicting Out-of-Distribution Performance of Deep Neural Networks Using Model Conformance-Reference-Cited by-同舟云学术

Predicting Out-of-Distribution Performance of Deep Neural Networks Using Model Conformance

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE International Conference on Assured Autonomy (ICAA)
language:
Short-container-title:

Author:

Kaur Ramneet¹,Jha Susmit²,Roy Anirban²,Sokolsky Oleg¹,Lee Insup¹

Affiliation:

1. University of Pennsylvania,Computer and Information Science,Philadelphia,USA

2. SRI International,Computer Science Laboratory,Menlo Park,USA

Funder

Army Research Laboratory

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10207556/10207559/10207589.pdf?arnumber=10207589

Reference42 articles.

1. Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization;miller;International Conference on Machine Learning,2021

2. Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systems

3. Over-parameterization improves robustness to covariate shift in high dimensions;tripuraneni;Advances in neural information processing systems,2021

4. Detecting OODs as Datapoints with High Uncertainty;kaur;arXiv preprint arXiv 2108 05935,2021

5. iDECODe: In-Distribution Equivariance for Conformal Out-of-Distribution Detection

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Memory-based Distribution Shift Detection for Learning Enabled Cyber-Physical Systems with Statistical Guarantees;ACM Transactions on Cyber-Physical Systems;2024-04-30

2. Out-of-Distribution Detection in Dependent Data for Cyber-Physical Systems with Conformal Guarantees;ACM Transactions on Cyber-Physical Systems;2024-02-13

3. Lightning Talk: Trinity - Assured Neuro-symbolic Model Inspired by Hierarchical Predictive Coding;2023 60th ACM/IEEE Design Automation Conference (DAC);2023-07-09