# Single Image Test-Time Adaptation for Segmentation

Source: [Single Image Test-Time Adaptation for Segmentation](<https://www.sota2.com/research/paper/68fa73e71e209131cea5ecc9>)

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

Data updated: 2025-10-27T06:35:02.634Z

Authors: Klara Janouskova, Tamir Shor, Chaim Baskin, Jiri Matas

Published: 2023-09-25T11:31:18.000Z

## Abstract

Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation. This work explores adapting segmentation models to a single unlabelled image with no other data available at test-time. In particular, this work focuses on adaptation by optimizing self-supervised losses at test-time. Multiple baselines based on different principles are evaluated under diverse conditions and a novel adversarial training is introduced for adaptation with mask refinement. Our additions to the baselines result in a 3.51 and 3.28 % increase over non-adapted baselines, without these improvements, the increase would be 1.7 and 2.16 % only.

## 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/2309.14052>)

[PDF](<https://arxiv.org/pdf/2309.14052.pdf>)