Robustness via Cross-Domain Ensembles

We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong prediction. The premise of the idea is...

Full description

Saved in:
Bibliographic Details
Main Authors: Yeo, Teresa, Kar, Oguzhan Fatih, Zamir, Amir
Format: Conference Proceeding
Language:English
Subjects:
Computer vision
Machine learning architectures and formulations
Merging
Neural networks
Robustness
Scene analysis and understanding
Task analysis
Training data
Uncertainty
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong prediction. The premise of the idea is that predictions made via different cues respond differently to a distribution shift, hence one should be able to merge them into one robust final prediction. We perform the merging in a straightforward but principled manner based on the uncertainty associated with each prediction. The evaluations are performed using multiple tasks and datasets (Taskonomy, Replica, ImageNet, CIFAR) under a wide range of adversarial and non-adversarial distribution shifts which demonstrate the proposed method is considerably more robust than its standard learning counterpart, conventional deep ensembles, and several other baselines.
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.01197