In this paper, we propose a method to improve real-time performance and accuracy by applying Edge Information Block (EIB) to the existing SegNet to perform real-time image segmentation. The proposed method was used in an experiment to improve performance by 23.5% in the Camvid data and 6.6%p in the DeepCrack data. And as a result of comparing with existing real-time image segmentation models, the calculation speed was seen to be improved by 50 to 150%, but the accuracy was found to be 1 to 6%p different. Through this experiment, it was proved that edge information enhances real-time and accuracy.
No takes yet. Share an insight, caveat, or question.
Jeon et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: