Umeå universitets logga

umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Out-of-Distribution Detection for Deep Neural Networks with Isolation Forest and Local Outlier Factor
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.ORCID-id: 0000-0003-4228-2774
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik. Department of Information Technologies and AI, Sirius University of Science and Technology, Sochi, Russian Federation.ORCID-id: 0000-0003-0730-9441
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
Visa övriga samt affilieringar
2021 (Engelska)Ingår i: IEEE Access, E-ISSN 2169-3536, Vol. 9, s. 132980-132989Artikel i tidskrift (Refereegranskat) 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.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers (IEEE), 2021. Vol. 9, s. 132980-132989
Nyckelord [en]
deep neural networks, isolation forest, local outlier factor, Out-of-distribution, outlier detection, runtime monitoring
Nationell ämneskategori
Datavetenskap (datalogi) Datorsystem
Identifikatorer
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
Tillgänglig från: 2022-01-13 Skapad: 2022-01-13 Senast uppdaterad: 2023-09-12Bibliografiskt granskad
Ingår i avhandling
1. Towards safe and efficient application of deep neural networks in resource-constrained real-time embedded systems
Öppna denna publikation i ny flik eller fönster >>Towards safe and efficient application of deep neural networks in resource-constrained real-time embedded systems
2023 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
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.

Ort, förlag, år, upplaga, sidor
Umeå: Umeå University, 2023. s. 49
Nyckelord
Machine Learning/Deep Learning, Real-Time Embedded systems, Out-of-Distribution Detection, Distribution Shifts, Deep Reinforcement Learning, Model Compression, Policy Distillation.
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:umu:diva-214365 (URN)978-91-8070-161-7 (ISBN)978-91-8070-160-0 (ISBN)
Disputation
2023-10-09, Triple Helix, Samverkanshuset, Umeå, 13:00 (Engelska)
Opponent
Handledare
Tillgänglig från: 2023-09-18 Skapad: 2023-09-12 Senast uppdaterad: 2023-09-13Bibliografiskt granskad

Open Access i DiVA

fulltext(5500 kB)908 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 5500 kBChecksumma SHA-512
f74cac924d93dc03433540fe1d57e65fb18188d521922bcbbb8f5a7434275369520ab5be9e902179f95335f348a3c64ca45276ac046ee1b75ab842322eefd06b
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextScopus

Person

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

Sök vidare i DiVA

Av författaren/redaktören
Luan, SiyuGu, ZonghuaFreidovich, Leonid B.Jiang, Lili
Av organisationen
Institutionen för tillämpad fysik och elektronikInstitutionen för datavetenskap
I samma tidskrift
IEEE Access
Datavetenskap (datalogi)Datorsystem

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 908 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 1921 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf