# StableTTA: Improving Vision Model Performance by Training-free Test-Time Adaptation Methods

Source: [StableTTA: Improving Vision Model Performance by Training-free Test-Time Adaptation Methods](<https://www.sota2.com/research/paper/69d48fb67d0172140ec744f2>)

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

Data updated: 2026-05-09T05:00:04.795Z

Authors: Zheng Li, Jerry Cheng, Huanying Helen Gu

Published: 2026-04-06T09:21:48.000Z

## Abstract

Ensemble methods improve predictive performance but often incur high memory and computational costs. We identify an aggregation instability induced by nonlinear projection and voting operations. To address both efficiency challenges and this inconsistency, we propose StableTTA, a training-free test-time adaptation method with two variants. StableTTA-I targets coherent-batch inference settings, where temporally or semantically adjacent observations are likely to belong to the same class. Examples include burst photography, video streams, robotics perception, and industrial inspection. Under coherent-batch inference, StableTTA-I substantially improves prediction consistency and accuracy through variance-aware logit aggregation. StableTTA-II establishes feature-level cropping, enabling efficient logit aggregation with a single forward pass on a single model backbone. Experiments on ImageNet-1K across 71 models demonstrate that StableTTA-I consistently improves prediction accuracy under coherent-batch inference, while StableTTA-II provides lightweight and architecture-agnostic accuracy improvements with minimal computational overhead. These results suggest that inference-time semantic coherence and aggregation stability provide useful perspectives for improving practical test-time adaptation systems.

## 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/2604.04552>)

[PDF](<https://arxiv.org/pdf/2604.04552.pdf>)
