Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applications

by   Yeli Feng, et al.

Uncertainties in machine learning are a significant roadblock for its application in safety-critical cyber-physical systems (CPS). One source of uncertainty arises from distribution shifts in the input data between training and test scenarios. Detecting such distribution shifts in real-time is an emerging approach to address the challenge. The high dimensional input space in CPS applications involving imaging adds extra difficulty to the task. Generative learning models are widely adopted for the task, namely out-of-distribution (OoD) detection. To improve the state-of-the-art, we studied existing proposals from both machine learning and CPS fields. In the latter, safety monitoring in real-time for autonomous driving agents has been a focus. Exploiting the spatiotemporal correlation of motion in videos, we can robustly detect hazardous motion around autonomous driving agents. Inspired by the latest advances in the Variational Autoencoder (VAE) theory and practice, we tapped into the prior knowledge in data to further boost OoD detection's robustness. Comparison studies over nuScenes and Synthia data sets show our methods significantly improve detection capabilities of OoD factors unique to driving scenarios, 42 generalized near-perfectly, 97 real-world and simulation driving data sets experimented. Finally, we customized one proposed method into a twin-encoder model that can be deployed to resource limited embedded devices for real-time OoD detection. Its execution time was reduced over four times in low-precision 8-bit integer inference, while detection capability is comparable to its corresponding floating-point model.


page 1

page 7

page 10

page 12


WiP Abstract : Robust Out-of-distribution Motion Detection and Localization in Autonomous CPS

Highly complex deep learning models are increasingly integrated into mod...

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

Cyber-physical systems (CPS) greatly benefit by using machine learning c...

Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression

Cyber-physical systems (CPSs) use learning-enabled components (LECs) ext...

Embedded out-of-distribution detection on an autonomous robot platform

Machine learning (ML) is actively finding its way into modern cyber-phys...

Out-of-Distribution Detection for Automotive Perception

Neural networks (NNs) are widely used for object recognition tasks in au...

Design Methodology for Deep Out-of-Distribution Detectors in Real-Time Cyber-Physical Systems

When machine learning (ML) models are supplied with data outside their t...

RTClean: Context-aware Tabular Data Cleaning using Real-time OFDs

Nowadays, machine learning plays a key role in developing plenty of appl...

Please sign up or login with your details

Forgot password? Click here to reset