Fully Convolutional Networks for Semantic Segmentation

By Evan Shelhamer, Jonathan Long, Trevor Darrell. 2017

1,912 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Fully convolutional networks for semantic segmentation (2014, methodology): “FCN extensions Following the conference version of this paper [17], FCNs have been extended to new tasks and data.”
Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network (2017, positive): “Initially, FCN [25] proposes the deconvolution (i.e. inverse of convolution) operation to increase the resolution of small score map.”
Proposal-Free Network for Instance-Level Object Segmentation (2015, positive): “Following the recent results of [1] [17], we have also utilized the multi-scale prediction to increase the instance location prediction accuracy.”
Recent advances in convolutional neural networks (2015, background): “-net [8] to obtain the distant and global features, and their concatenation gives rise to the zoom-out features. They achieve very competitive results on the semantic segmentation tasks. Long et al . [28] train a fully convolutional Network to directly predict the input images to dense label maps. T”
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection (2014, neutral): “However, since we claim that these two tasks are mutually related, we propose to invert this process.”
Pathology Image Analysis Using Segmentation Deep Learning Algorithms. (2019, methodology): “13,14 Compared with multilabel classi ﬁ cation algorithms, which can identify 15 and locate 16 objects of different types, the segmentation deep learning algorithms detect not only the objects but also the segmentation boundaries.”
Computer-aided detection in chest radiography based on artificial intelligence: a survey (2018, methodology): “The current application of a more semantic segmentation method is the fully convolutional network (FCN) [48], which retains the advantageous features of SegNet [49], accepts input of any size, and produces output of the same size.”
Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective (2018, positive): “proposed an FCN that enables end-to-end training for sematic image segmentation by pixel-wise object labeling [85], which has been applied to generate weed distribution maps from UAV images [86, 87].”
Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation (2019, methodology): “Method data pixel-acc mean-acc IoU FCN [40] RGB 60.”
Recent developments in deep learning applied to protein structure prediction (2019, methodology): “This is achieved using fully convolutional networks (FCNs; not to be confused with fully connected networks), 43 which are simply composed of a stack of convolutional layers all the way up to the output, omitting max pooling or fully connected layers that either change the image resolution or lose…”
OCNet: Object Context for Semantic Segmentation (2021, methodology): “Extensive efforts based on deep convolutional neural networks have been made to address the semantic segmentation Communicated by Cha Zhang. since the pioneering approach of the fully convolutional network (FCN) (Shelhamer et al. 2017).”