Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Jackson Darrell · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2015
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 [20], the VGG net [31], and GoogLeNet [32]) into fully convolutional networks and transfer their learned representations by fine-tuning [3] 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.
Cited by 36,250 works. doi:10.1109/cvpr.2015.7298965
Authors
References
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Going deeper with convolutions
- Backpropagation Applied to Handwritten Zip Code Recognition
- Caffe
- Visualizing and Understanding Convolutional Networks
- A Wavelet Tour of Signal Processing
- Book Review: Pattern Recognition and Machine Learning
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition