Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Out-of-Distribution Detection for Deep Neural Networks with Isolation Forest and Local Outlier Factor
Umeå University, Faculty of Science and Technology, Department of Applied Physics and Electronics.
Umeå University, Faculty of Science and Technology, Department of Applied Physics and Electronics.ORCID iD: 0000-0003-4228-2774
Umeå University, Faculty of Science and Technology, Department of Applied Physics and Electronics. Department of Information Technologies and AI, Sirius University of Science and Technology, Sochi, Russian Federation.ORCID iD: 0000-0003-0730-9441
Umeå University, Faculty of Science and Technology, Department of Computing Science.
Show others and affiliations
2021 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 9, p. 132980-132989Article in journal (Refereed) Published
Abstract [en]

Deep Neural Networks (DNNs) are extensively deployed in today's safety-critical autonomous systems thanks to their excellent performance. However, they are known to make mistakes unpredictably, e.g., a DNN may misclassify an object if it is used for perception, or issue unsafe control commands if it is used for planning and control. One common cause for such unpredictable mistakes is Out-of-Distribution (OOD) input samples, i.e., samples that fall outside of the distribution of the training dataset. We present a framework for OOD detection based on outlier detection in one or more hidden layers of a DNN with a runtime monitor based on either Isolation Forest (IF) or Local Outlier Factor (LOF). Performance evaluation indicates that LOF is a promising method in terms of both the Machine Learning metrics of precision, recall, F1 score and accuracy, as well as computational efficiency during testing.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2021. Vol. 9, p. 132980-132989
Keywords [en]
deep neural networks, isolation forest, local outlier factor, Out-of-distribution, outlier detection, runtime monitoring
National Category
Computer Sciences Computer Systems
Identifiers
URN: urn:nbn:se:umu:diva-191334DOI: 10.1109/ACCESS.2021.3108451ISI: 000702542000001Scopus ID: 2-s2.0-85113855730OAI: oai:DiVA.org:umu-191334DiVA, id: diva2:1627522
Available from: 2022-01-13 Created: 2022-01-13 Last updated: 2023-09-12Bibliographically approved
In thesis
1. Towards safe and efficient application of deep neural networks in resource-constrained real-time embedded systems
Open this publication in new window or tab >>Towards safe and efficient application of deep neural networks in resource-constrained real-time embedded systems
2023 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

We consider real-time safety-critical systems that feature closed-loop interactions between the embedded computing system and the physical environment with a sense-compute-actuate feedback loop. Deep Learning (DL) with Deep Neural Networks (DNNs) has achieved success in many application domains, but there are still significant challenges in its application in real-time safety-critical systems that require high levels of safety certification under significant hardware resource constraints. This thesis considers the following overarching research goal: How to achieve safe and efficient application of DNNs in resource-constrained Real-Time Embedded (RTE) systems in the context of safety-critical application domains such as Autonomous Driving? Towards reaching that goal, this thesis presents a set of algorithms and techniques that aim to address three Research Questions (RQs): RQ1: How to achieve accurate and efficient Out-of-Distribution (OOD) detection for DNNs in RTE systems? RQ2: How to predict the performance of DNNs under continuous distribution shifts? RQ3: How to achieve efficient inference of Deep Reinforcement Learning (DRL) agents in RTE systems?

For RQ1, we present a framework for OOD detection based on outlier detection in one or more hidden layers of a DNN with either Isolation Forest (IF) or Local Outlier Factor (LOF). We also perform a comprehensive and systematic benchmark study of multiple well-known OOD detection algorithms in terms of both accuracy and execution time on different hardware platforms, in order to provide a useful reference for the practical deployment of OOD detection algorithms in RTE systems. For RQ2, we present a framework for predicting the performance of DNNs for end-to-end Autonomous Driving under continuous distribution shifts with two approaches: using an Autoencoder that attempts to reconstruct the input image; and applying Anomaly Detection algorithms to the hidden layer(s) of the DNN. For RQ3, we present a framework for model compression of the policy network of a DRL agent for deployment in RTE systems by leveraging the relevance scores computed by Layer-wise Relevance Propagation (LRP) to rank and prune the convolutional filters, combined with fine-tuning using policy distillation.

The algorithms and techniques developed in this thesis have been evaluated on standard datasets and benchmarks. To summarize our findings, we have developed novel OOD detection algorithms with high accuracy and efficiency; identified OOD detection algorithms with relatively high accuracy and low execution times through benchmarking; developed a framework for DNN performance prediction under continuous distribution shifts, and identified most effective Anomaly Detection algorithms for use in the framework; developed a framework for model compression of DRL agents that is effective in reducing model size and inference time for deployment in RTE systems. The research results are expected to assist system designers in the task of safe and efficient application of DNNs in resource-constrained RTE systems.

Place, publisher, year, edition, pages
Umeå: Umeå University, 2023. p. 49
Keywords
Machine Learning/Deep Learning, Real-Time Embedded systems, Out-of-Distribution Detection, Distribution Shifts, Deep Reinforcement Learning, Model Compression, Policy Distillation.
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-214365 (URN)978-91-8070-161-7 (ISBN)978-91-8070-160-0 (ISBN)
Public defence
2023-10-09, Triple Helix, Samverkanshuset, Umeå, 13:00 (English)
Opponent
Supervisors
Available from: 2023-09-18 Created: 2023-09-12 Last updated: 2023-09-13Bibliographically approved

Open Access in DiVA

fulltext(5500 kB)835 downloads
File information
File name FULLTEXT01.pdfFile size 5500 kBChecksum SHA-512
f74cac924d93dc03433540fe1d57e65fb18188d521922bcbbb8f5a7434275369520ab5be9e902179f95335f348a3c64ca45276ac046ee1b75ab842322eefd06b
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Luan, SiyuGu, ZonghuaFreidovich, Leonid B.Jiang, Lili

Search in DiVA

By author/editor
Luan, SiyuGu, ZonghuaFreidovich, Leonid B.Jiang, Lili
By organisation
Department of Applied Physics and ElectronicsDepartment of Computing Science
In the same journal
IEEE Access
Computer SciencesComputer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 835 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 1867 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf