Learning Deconvolution Network for Semantic Segmentation

ICCV 2015 Hyeonwoo NohSeunghoon HongBohyung Han

We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Curved Text Detection SCUT-CTW1500 CTD+TLOC [[Noh et al.(2015)Noh, Hong, and Han]] F-Measure 73.4% # 3
Curved Text Detection SCUT-CTW1500 CTD [[Noh et al.(2015)Noh, Hong, and Han]] F-Measure 69.5% # 4