CSIPlab / MMSFormer

We propose a novel fusion strategy that can effectively fuse information from different modality combinations. We also propose a new model named Multi-Modal Segmentation TransFormer (MMSFormer) that incorporates the proposed fusion strategy to perform multimodal material and semantic segmentation tasks.
12Updated 10 months ago

Alternatives and similar repositories for MMSFormer:

Users that are interested in MMSFormer are comparing it to the libraries listed below