Bootstrap Your Own Variance
CoRR(2023)
Abstract
Understanding model uncertainty is important for many applications. We
propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent
(BYOL), a negative-free Self-Supervised Learning (SSL) algorithm, with Bayes by
Backprop (BBB), a Bayesian method for estimating model posteriors. We find that
the learned predictive std of BYOV vs. a supervised BBB model is well captured
by a Gaussian distribution, providing preliminary evidence that the learned
parameter posterior is useful for label free uncertainty estimation. BYOV
improves upon the deterministic BYOL baseline (+2.83% test ECE, +1.03% test
Brier) and presents better calibration and reliability when tested with various
augmentations (eg: +2.4% test ECE, +1.2% test Brier for Salt & Pepper noise).
MoreTranslated text
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined