Label Calibration for Semantic Segmentation Under Domain Shift
This addresses the domain adaptation problem for semantic segmentation, offering a practical solution for real-world applications, though it appears incremental as it builds on existing prototype-based methods.
The paper tackles the problem of semantic segmentation performance dropping under domain shift by proposing a fast, low-cost adaptation method using soft-label prototypes, achieving considerable performance improvements on synthetic-to-real segmentation tasks.
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.