# Label Calibration for Semantic Segmentation Under Domain Shift

Source: [Label Calibration for Semantic Segmentation Under Domain Shift](<https://www.sota2.com/research/paper/68fa70181e209131cea48ef0>)

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

Data updated: 2025-10-26T01:33:16.495Z

Authors: Ondrej Bohdal, Da Li, Timothy Hospedales

Published: 2023-07-20T13:02:45.000Z

## Abstract

Performance of a pre-trained semantic segmentation model is likely to substantially decrease on data from a new domain. We show a pre-trained model can be adapted to unlabelled target domain data by calculating soft-label prototypes under the domain shift and making predictions according to the prototype closest to the vector with predicted class probabilities. The proposed adaptation procedure is fast, comes almost for free in terms of computational resources and leads to considerable performance improvements. We demonstrate the benefits of such label calibration on the highly-practical synthetic-to-real semantic segmentation problem.

## 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/2307.10842>)

[PDF](<https://arxiv.org/pdf/2307.10842.pdf>)