Fully Convolutional Networks for Semantic Segmentation
No Thumbnail Available
Date
2015-11-14
Journal Title
Journal ISSN
Volume Title
Publisher
arXiv
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 novel 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 one third of a second for a typical image.
Description
FCN은 이미지 크기를 입력 그대로 유지하면서 픽셀 단위 분할이 가능한 네트워크로, 직접 분할 모델 학습이 가능하다는 것을 제안했습니다
Keywords
Fully Convolutional Network, Semantic Segmentation, CNN, FCN, Deep Learning