ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

ECCV 2018 Sachin MehtaMohammad RastegariAnat CaspiLinda ShapiroHannaneh Hajishirzi

We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is efficient in terms of computation, memory, and power... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Semantic Segmentation Cityscapes test ESPNet Mean IoU (class) 60.3% # 61
Semantic Segmentation PASCAL VOC 2012 test ESPNet Mean IoU 63.01% # 38

Methods used in the Paper