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).

翻译：理解模型不确定性对于许多应用至关重要。我们提出引导自身方差（BYOV），该方法将无负样本自监督学习（SSL）算法“引导自身潜变量”（BYOL）与用于估计模型后验的贝叶斯方法“反向传播贝叶斯”（BBB）相结合。研究发现，BYOV学习到的预测标准差与监督式BBB模型的结果能够很好地服从高斯分布，这为所学习的参数后验在无标签不确定性估计中的有效性提供了初步证据。BYOV相较于确定性BYOL基线模型表现更优（测试集ECE提升2.83%，测试集Brier得分提升1.03%），并在多种数据增强条件下展现出更好的校准性与可靠性（例如：对椒盐噪声的测试集ECE提升2.4%，Brier得分提升1.2%）。