AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

MIRA: Mutual Information guided calibration for Reliable Test-Time Adaptation

Hyeongyu Kim, Mingyeong Jang, Youngjun Song, GeonHui Han, Dosik Hwang

NeurIPS 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Realistic and stable test-time adaptation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MIRA, a source-free online test-time adaptation method that uses mutual information from lightweight last-layer Gaussian perturbations to guide calibrated, more reliable adaptation under distribution shift.

Problem

Test-time adaptation with only unlabeled target data; standard entropy-based methods rely on deterministic confidence and can reinforce overconfident errors under distribution shift.

Approach

Uses lightweight last-layer Gaussian perturbations to probe predictive uncertainty via mutual information, instead of deterministic entropy, to guide source-free online adaptation and calibration.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
attach MIRA reliability gateTENT · CIFAR-100-C ResNeXtaccuracy (%): 67.84 -> 68.69Improved
attach MIRA reliability gateEATA · ImageNet-C ResNet-50accuracy (%): 40.02 -> 43.18Improved
attach MIRA reliability gateROID · CIFAR-100-C ResNeXtaccuracy (%): 69.16 -> 69.21No clear effect
attach MIRA reliability gateSAR · ImageNet-C ResNet-50accuracy (%): 36.72 -> 39.28Improved
minimize MI directly as the loss (ablation)MIRA+TENT · ImageNet-C (loss ablation)accuracy: 0.3421 -> 0.2977Hurt
use HE only or EH only instead of TENT entropy (ablation)MIRA+TENT · ImageNet-C (loss ablation)accuracy: 0.3421 -> 0.3408No clear effect
combine HE and EH losses (ablation)MIRA+TENT · ImageNet-C (loss ablation)accuracy: 0.3408 -> 0.3637Improved
add MI weight w_MI to HE+EH (ablation)MIRA+TENT · ImageNet-C (loss ablation)accuracy: 0.3637 -> 0.3658No clear effect
add confidence gate on top of MI weight (ablation)MIRA+TENT · ImageNet-C (loss ablation)accuracy: 0.3658 -> 0.3699Improved
perturb last 2-3 layers instead of classifier only (ablation)MIRA · ImageNet-C ResNet-34ECE: 0.0458 -> 0.0649Hurt
increase Monte Carlo samples K from 100 to 1000 (ablation)MIRA · ImageNet-C ResNet-50accuracy (%): 29.55 -> 29.76No clear effect
add MIRA to continual CoTTACoTTA · CIFAR-100-C continualaccuracy (%): 64.16 -> 65.20Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Experimental setup

Baselines: entropy-based test-time adaptation methods

Builds on: entropy minimization

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy