Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation

About

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.

Fuqin Deng, Hua Feng, Mingjian Liang, Hongmin Wang, Yong Yang, Yuan Gao, Junfeng Chen, Junjie Hu, Xiyue Guo, Tin Lun Lam• 2021

Related benchmarks

TaskDatasetResultRank
Semantic segmentationMFNet (test)
mIoU55.3
134
Semantic segmentationPST900 (test)
mIoU85.5
72
Semantic segmentationFMB (test)
mIoU46.8
59
Semantic segmentationMFNet day-night (test)
Car IoU87.8
20
Semantic segmentationMFNet
mIoU55.3
13
Semantic segmentationMFNet RGB-T 2017 (test)
mIoU55.3
13
Semantic segmentationMF day-night 11 (evaluation set)
Unlabeled IoU98.3
12
Scene ParsingPST900 (test)
mIoU85.5
11
RGB-T Semantic SegmentationMFNet
Latency (ms)28.52
4
Showing 9 of 9 rows

Other info

Follow for update