DeepLab
A series of semantic segmentation models that employ techniques such as atrous convolution and spatial pyramid pooling, achieving strong performance on multiple segmentation benchmarks.
Timeline (last 90 days)
Image segmentation is divided into semantic segmentation (such as U-Net and DeepLab) and instance segmentation (such as Mask R-CNN).
ASPP (Atrous Spatial Pyramid Pooling) was proposed in the DeepLab series of works and uses multiple parallel atrous convolutions with different dilation rates to extract multi-scale contextual information.
All Facts (2)
Image segmentation is divided into semantic segmentation (such as U-Net and DeepLab) and instance segmentation (such as Mask R-CNN).
50%UnverifiedASPP (Atrous Spatial Pyramid Pooling) was proposed in the DeepLab series of works and uses multiple parallel atrous convolutions with different dilation rates to extract multi-scale contextual information.
50%