Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning

TL;DR

This paper introduces Uncertainty Baselines, a comprehensive collection of implementations, benchmarks, and tools for evaluating uncertainty and robustness in deep learning models across multiple tasks.

Contribution

It provides a standardized, reproducible framework with diverse baselines, metrics, and resources to facilitate research and comparison in uncertainty estimation and robustness.

Findings

19 methods across 9 tasks with 5+ metrics each

Reusable experiment pipelines and checkpoints provided

Leaderboards enable straightforward comparison of techniques

Abstract

High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ability to compare techniques for improving these estimates is therefore very important for research and practice alike. Yet, competitive comparisons of methods are often lacking due to a range of reasons, including: compute availability for extensive tuning, incorporation of sufficiently many baselines, and concrete documentation for reproducibility. In this paper we introduce Uncertainty Baselines: high-quality implementations of standard and state-of-the-art deep learning methods on a variety of tasks. As of this writing, the collection spans 19 methods across 9 tasks, each with at least 5 metrics. Each baseline is a self-contained experiment pipeline with easily reusable and extendable components. Our goal is to provide immediate starting points for experimentation with new methods or applications. Additionally we provide model checkpoints, experiment outputs as Python notebooks, and leaderboards for comparing results. Code available at https://github.com/google/uncertainty-baselines.