FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation
This work addresses the need for accurate and fast semantic segmentation in urban scenes using RGB-Thermal data, representing an incremental improvement over existing methods.
The paper tackles the problem of poor performance in real-time RGB-Thermal semantic segmentation due to compromised spatial resolution, proposing FEANet which improves global mAcc by 2.6% and mIoU by 0.8% while maintaining real-time speed.
The RGB-Thermal (RGB-T) information for semantic segmentation has been extensively explored in recent years. However, most existing RGB-T semantic segmentation usually compromises spatial resolution to achieve real-time inference speed, which leads to poor performance. To better extract detail spatial information, we propose a two-stage Feature-Enhanced Attention Network (FEANet) for the RGB-T semantic segmentation task. Specifically, we introduce a Feature-Enhanced Attention Module (FEAM) to excavate and enhance multi-level features from both the channel and spatial views. Benefited from the proposed FEAM module, our FEANet can preserve the spatial information and shift more attention to high-resolution features from the fused RGB-T images. Extensive experiments on the urban scene dataset demonstrate that our FEANet outperforms other state-of-the-art (SOTA) RGB-T methods in terms of objective metrics and subjective visual comparison (+2.6% in global mAcc and +0.8% in global mIoU). For the 480 x 640 RGB-T test images, our FEANet can run with a real-time speed on an NVIDIA GeForce RTX 2080 Ti card.