Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations

Anumasa, Srinivas and Srijith, P K (2021) Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations. In: 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021, 5 January 2021 through 9 January 2021, Virtual, Online.

[img] Text
Proceedings_2021.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB)


Deep learning models such as Resnets have resulted in state-of-the-art accuracy in many computer vision problems. Neural ordinary differential equations (NODE) provides a continuous depth generalization of Resnets and overcome drawbacks of Resnet such as model selection and parameter complexity. Though NODE is more robust than Resnet, we find that NODE based architectures are still far away from providing robustness and uncertainty handling required for many computer vision problems. We propose novel NODE models which address these drawbacks. In particular, we propose Gaussian processes (GPs) to model the fully connected neural networks in NODE (NODE-GP) to improve robustness and uncertainty handling capabilities of NODE. The proposed model is flexible to accommodate different NODE architectures, and further improves the model selection capabilities in NODEs. We also find that numerical techniques play an important role in modelling NODE robustness, and propose to use different numerical techniques to improve NODE robustness. We demonstrate the superior robustness and uncertainty handling capabilities of proposed models on adversarial attacks and out-of-distribution experiments for the image classification tasks. © 2021 IEEE.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Srijith, P K
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Computer vision problems; Generalisation; Handling capability; Learning models; Model Selection; Modeling parameters; Numerical techniques; State of the art; Uncertainty handling; Uncertainty models
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 27 Aug 2022 11:38
Last Modified: 27 Aug 2022 11:38
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 10318 Statistics for this ePrint Item