Rethinking Early-Fusion Strategies for Improved Multimodal Image Segmentation
This work addresses the computational inefficiency in multimodal segmentation for applications like low-illumination imaging, offering an incremental improvement over existing methods.
The paper tackles the problem of inefficient multimodal image segmentation by proposing a novel early fusion network (EFNet) with feature clustering and a lightweight decoder, achieving state-of-the-art performance with reduced parameters and computation on RGB-T datasets.
RGB and thermal image fusion have great potential to exhibit improved semantic segmentation in low-illumination conditions. Existing methods typically employ a two-branch encoder framework for multimodal feature extraction and design complicated feature fusion strategies to achieve feature extraction and fusion for multimodal semantic segmentation. However, these methods require massive parameter updates and computational effort during the feature extraction and fusion. To address this issue, we propose a novel multimodal fusion network (EFNet) based on an early fusion strategy and a simple but effective feature clustering for training efficient RGB-T semantic segmentation. In addition, we also propose a lightweight and efficient multi-scale feature aggregation decoder based on Euclidean distance. We validate the effectiveness of our method on different datasets and outperform previous state-of-the-art methods with lower parameters and computation.