- Task 1 - Track 1 – Single-domain training (Models must be trained exclusively on the published Cityscapes dataset) - Method: PixOOD w/ DeepLab Decoder
- Method info
- Samples list
- Per sample details
method: PixOOD w/ DeepLab Decoder2024-08-22
Authors: Tomáš Vojíř , Jan Šochman , and Jiří Matas
Affiliation: Czech Technical University in Prague
Description: This method is based on PixOOD but replace the simple MLP for semantic segmentation with more complex decoder from DeepLab v3 architecture.
The details and differences w.r.t the PixOOD are described in the technical paper.