Fully Convolutional Networks for Semantic Segmentation
Top Cited Papers
Open Access
- 24 May 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 39 (4), 640-651
- https://doi.org/10.1109/tpami.2016.2572683
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, improve on the previous best result 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 networks achieve improved segmentation of PASCAL VOC (30% relative improvement to 67.2% mean IU on 2012), NYUDv2, SIFT Flow, and PASCAL-Context, while inference takes one tenth of a second for a typical image.Keywords
Other Versions
Funding Information
- DARPA's MSEE
- SMISC
- US National Science Foundation (IIS-1427425, IIS-1212798, IIS-1116411)
- NSF
- GRFP
- Toyota
- Berkeley Vision and Learning Center
- Nvidia
- GPU
- SIFT
- IU
- IU
This publication has 29 references indexed in Scilit:
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Constrained Convolutional Neural Networks for Weakly Supervised SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Holistically-Nested Edge DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Convolutional feature masking for joint object and stuff segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Feedforward semantic segmentation with zoom-out featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- The Role of Context for Object Detection and Semantic Segmentation in the WildPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Pedestrian Detection with Unsupervised Multi-stage Feature LearningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Representation of local geometry in the visual systemBiological Cybernetics, 1987