The AttendSeg deep learning model performs semantic segmentation at an accuracy that is almost on-par with RefineNet while cutting down the number of parameters to 1.19 million.

To improve the semantic boundary accuracy, we propose low complexity Deep Guided Decoder (DGD) networks, trained with a novel Semantic Boundary-Aware Learning (SBAL) strategy. Our ablation studies on ...

The transformer-based semantic segmentation approaches, which divide the image into different regions by sliding windows and model the relation inside each window, have achieved outstanding ...