Papers › Fully Convolutional Networks for Semantic Segmentation

Fully Convolutional Networks for Semantic Segmentation

20 May 2016CVPR 2015arXiv:1605.06211archive 2025-07-28

Evan Shelhamer, Jonathan Long, Trevor Darrell

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 network achieves 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.

PaperPDFCode

Code

37 repositories listed; official and paper-mentioned ones first.

AzogDefiler/Sandbox mentioned on GitHub report
ChenMicky/FCN mentioned on GitHubtf report
Lxrd-AJ/Advanced_ML mentioned on GitHubpytorch report
Osdel/ssnets mentioned on GitHubtf report
TejasBajania/Mtech_pro mentioned on GitHub report
cooparation/FCN_play mentioned on GitHub report
fmahoudeau/fcn mentioned on GitHubtf report
geodekid/FCN mentioned on GitHubcaffe2 report
kevinddchen/Keras-FCN mentioned on GitHubtf report
rickyHong/FCN-segmentation-repl mentioned on GitHubcaffe2 report
shekkizh/FCN.tensorflow mentioned on GitHubtf report
shelhamer/fcn.berkeleyvision.org mentioned on GitHubcaffe2 report
waspinator/deep-learning-explorer mentioned on GitHubApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Real-Time Semantic SegmentationScene SegmentationSegmentationSemantic SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Segmentation SUN-RGBD FCN Mean IoU 27.39 #5 of 5 Archive leaderboard report
Semantic Segmentation Cityscapes test FCN Mean IoU (class) 65.3% #95 of 105 Archive leaderboard report
Semantic Segmentation NYU Depth v2 FCN-32s RGB-HHA Mean Accuracy 44 #121 of 121 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2011 test FCN-VGG16 Mean IoU 32 #2 of 3 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2011 test FCN-pool4 Mean IoU 22.4 #3 of 3 Archive leaderboard report
Video Semantic Segmentation Cityscapes val FCN-50 [14] mIoU 70.1 #8 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: FCN, Transposed convolution

ConvolutionDense ConnectionsDropoutFCNMax PoolingReLUSoftmaxTransposed convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections