Superpixel Positional Encoding to Improve ViT-based Semantic Segmentation Models

Citation:

Amoroso, Roberto; Tomei, Matteo; Baraldi, Lorenzo; Cucchiara, Rita "Superpixel Positional Encoding to Improve ViT-based Semantic Segmentation Models" Proceedings of the British Machine Vision Conference 2023, Aberdeen, UK, 20th - 24th November 2023, 2023

 not available

Paper download:

• Author version: