MMSFormer: Multimodal Transformer for Material and Semantic Segmentation
This work addresses the problem of multimodal segmentation for material and semantic identification, offering incremental improvements in fusion techniques for domain-specific applications.
The paper tackles the challenge of effectively fusing information from diverse modalities for multimodal segmentation tasks by proposing a novel fusion strategy and a model called MMSFormer, which outperforms state-of-the-art models on three datasets and shows progressive performance improvements as more modalities are added.
Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of each modality. In this paper, 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. MMSFormer outperforms current state-of-the-art models on three different datasets. As we begin with only one input modality, performance improves progressively as additional modalities are incorporated, showcasing the effectiveness of the fusion block in combining useful information from diverse input modalities. Ablation studies show that different modules in the fusion block are crucial for overall model performance. Furthermore, our ablation studies also highlight the capacity of different input modalities to improve performance in the identification of different types of materials. The code and pretrained models will be made available at https://github.com/csiplab/MMSFormer.