# SBNet: Sparse Blocks Network for Fast Inference

Mengye RenAndrei PokrovskyBin YangRaquel Urtasun

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such as object detection and semantic segmentation, we are able to obtain a low-cost computation mask, either from a priori problem knowledge, or from a low-resolution segmentation network... (read more)

PDF Abstract

408