MMSFormer: Multimodal Transformer for Material and Semantic Segmentation
arXiv:2309.04001 · doi:10.1109/OJSP.2024.3389812
Abstract
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.
arXiv commentAccepted by IEEE Open Journal of Signal Processing. 15 pages, 3 figures, 9 tables
References in corpus (5)
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- A Survey on Instance Segmentation: State of the art
- DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion
- FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
- RGB-T Semantic Segmentation with Location, Activation, and Sharpening