图像分割(一)——Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
Axial-DeepLab:Stand-AloneAxial-AttentionforPanopticSegmentationAbstract1IntroductionMethodPosition-SensitiveSelf-AttentionAxial-Attention纯transformer框架的全景分割Abstract卷积利用局部性来提高效率,但代价是丢失长范围上下文。自注意力通过非局部的