Fully Convolutional Networks for Semantic Segmentation

TitleFully Convolutional Networks for Semantic Segmentation
Publication TypeConference Paper
Year of Publication2015
AuthorsLong, J., Shelhamer E., & Darrell T.
Published inThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Page(s)3431-3440
Date Published06/2015
Abstract

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes less than one fifth of a second for a typical image.

URLhttp://www.icsi.berkeley.edu/pubs/vision/fullyconvolutional15.pdf
ICSI Research Group

Vision