# Asymmetric Duos: Sidekicks Improve Uncertainty

Source: [Asymmetric Duos: Sidekicks Improve Uncertainty](<https://www.sota2.com/research/paper/68fa78c91e209131cea7a878>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-28T05:01:13.271Z

Authors: Tim G. Zhou, Evan Shelhamer, Geoff Pleiss

Published: 2025-05-24T10:49:19.000Z

## Abstract

The go-to strategy to apply deep networks in settings where uncertainty informs decisions--ensembling multiple training runs with random initializations--is ill-suited for the extremely large-scale models and practical fine-tuning workflows of today. We introduce a new cost-effective strategy for improving the uncertainty quantification and downstream decisions of a large model (e.g. a fine-tuned ViT-B): coupling it with a less accurate but much smaller "sidekick" (e.g. a fine-tuned ResNet-34) with a fraction of the computational cost. We propose aggregating the predictions of this Asymmetric Duo by simple learned weighted averaging. Surprisingly, despite their inherent asymmetry, the sidekick model almost never harms the performance of the larger model. In fact, across five image classification benchmarks and a variety of model architectures and training schemes (including soups), Asymmetric Duos significantly improve accuracy, uncertainty quantification, and selective classification metrics with only ${\\sim}10-20\\%$ more computation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.18636>)

[PDF](<https://arxiv.org/pdf/2505.18636.pdf>)
