Abstract
Out-of-distribution (OOD) detectors can act as safety monitors in embedded cyber-physical systems by identifying samples outside a machine learning model's training distribution to prevent potentially unsafe actions. However, OOD detectors are often implemented using deep neural networks, which makes it difficult to meet real-time deadlines on embedded systems with memory and power constraints. We consider the class of variational autoencoder (VAE) based OOD detectors where OOD detection is performed in latent space, and apply quantization, pruning, and knowledge distillation. These techniques have been explored for other deep models, but no work has considered their combined effect on latent space OOD detection. While these techniques increase the VAE's test loss, this does not correspond to a proportional decrease in OOD detection performance and we leverage this to develop lean OOD detectors capable of real-time inference on embedded CPUs and GPUs. We propose a design methodology that combines all three compression techniques and yields a significant decrease in memory and execution time while maintaining AUROC for a given OOD detector. We demonstrate this methodology with two existing OOD detectors on a Jetson Nano and reduce GPU and CPU inference time by 20% and 28% respectively while keeping AUROC within 5% of the baseline.
Original language | English |
---|---|
Title of host publication | Proceedings - 2024 IEEE 30th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2024 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 37-42 |
Number of pages | 6 |
ISBN (Electronic) | 9798350387957 |
DOIs | |
Publication status | Published - 2024 |
Externally published | Yes |
Event | 30th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2024 - Sokcho, Korea, Republic of Duration: Aug 21 2024 → Aug 23 2024 |
Publication series
Name | Proceedings - 2024 IEEE 30th International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2024 |
---|
Conference
Conference | 30th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2024 |
---|---|
Country/Territory | Korea, Republic of |
City | Sokcho |
Period | 8/21/24 → 8/23/24 |
Bibliographical note
Publisher Copyright:© 2024 IEEE.
ASJC Scopus Subject Areas
- Computer Networks and Communications
- Computer Science Applications
- Hardware and Architecture
- Information Systems and Management