Label Calibration for Semantic Segmentation Under Domain ShiftDownload PDF

Published: 04 Mar 2023, Last Modified: 28 Mar 2023ICLR 2023 Workshop on Trustworthy ML PosterReaders: Everyone
Keywords: Semantic segmentation, domain adaptation, source-free, synthetic-to-real
TL;DR: Fast method for adapting a pre-trained semantic segmentation model using soft-label prototypes
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.
0 Replies

Loading