CVPRApr, 2024

多视角聚合网络用于二分图像分割

TL;DRDichotomous Image Segmentation (DIS) explores the challenge of balancing semantic dispersion and high-precision details in object segmentation. The paper proposes a parsimonious multi-view aggregation network (MVANet) that surpasses state-of-the-art methods in accuracy and speed.