Label Calibration for Semantic Segmentation Under Domain Shift

Ondrej Bohdal, Da Li, Timothy Hospedales

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationICLR 2023 Workshop on Pitfalls of limited data and computation for Trustworthy ML
Pages1-6
Publication statusPublished - 4 Mar 2023
EventICLR 2023 Workshop on Pitfalls of limited data and computation for Trustworthy ML - Kigali, Rwanda
Duration: 5 May 2023 → …
Conference number: 11
https://iclr.cc/virtual/2023/workshop/12844

Workshop

WorkshopICLR 2023 Workshop on Pitfalls of limited data and computation for Trustworthy ML
Country/TerritoryRwanda
CityKigali
Period5/05/23 → …
Internet address

Fingerprint

Dive into the research topics of 'Label Calibration for Semantic Segmentation Under Domain Shift'. Together they form a unique fingerprint.

Cite this