Papers › Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

22 Dec 2014arXiv:1412.7062archive 2025-07-28

Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L. Yuille

Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "semantic image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1412.7062")

Code

Syntology Ran 0 of 1 code samples harvested from 1 repository linked to this paper; 1 has no recorded run.

By repository: community (archive-listed): 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

bitbucket.org/deeplab/deeplab-public officialmentioned in paper report
BardOfCodes/pytorch_deeplab_large_fov mentioned on GitHubpytorch report
Daeijavad/Deeplab-CRF mentioned on GitHubtf report
DeepMotionAIResearch/DenseASPP mentioned on GitHubpytorch report
Jasonlee1995/DeepLab_v1 mentioned on GitHubpytorch report
NASA-NeMO-Net/NeMO-Net mentioned on GitHubtf report
TheLegendAli/DeepLab-Context mentioned on GitHubNOASSERTION report
nightrome/cocostuff10k mentioned on GitHub report
open-cv/deeplab-v1 mentioned on GitHubNOASSERTION report
pathak22/ccnn mentioned on GitHubNOASSERTION report
tensorflow/models mentioned on GitHubtf report
tensorflow/models mentioned on GitHubtf report
wangleihitcs/DeepLab-V1-PyTorch mentioned on GitHubpytorch report
open-mmlab/mmsegmentation pytorchApache-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

1 sample harvested; 0 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1unverified

Licence: 1 of the 1 sample is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from arahusky/Tensorflow-Segmentation. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

draw_results arahusky/Tensorflow-Segmentation/convolutional_autoencoder.py community (archive-listed) unverified no licence file found · pointer only · 9bf5955c8ae6f932 · report

Tasks

Image SegmentationSegmentationSemantic Segmentationimage-classificationobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation CamVid DeepLab Frame (fps) 4.9 #27 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid DeepLab Time (ms) 203 #27 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid DeepLab mIoU 61.6% #27 of 29 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test DeepLab Frame (fps) 0.25 #37 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test DeepLab Time (ms) 4000 #37 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test DeepLab mIoU 63.1% #37 of 39 Archive leaderboard report
Scene Segmentation SUN-RGBD DeepLab-LargeFOV Mean IoU 32.08 #3 of 5 Archive leaderboard report
Semantic Segmentation CamVid DeepLab-MSc-CRF-LargeFOV Mean IoU 61.6% #19 of 21 Archive leaderboard report
Semantic Segmentation Cityscapes test DeepLab Mean IoU (class) 63.1% #98 of 105 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test DeepLab-MSc-CRF-LargeFOV (VGG-16) Mean IoU 71.6% #38 of 51 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

CRFConvolutionDeepLabDense ConnectionsDropoutFeedforward NetworkMax PoolingReLUSGD with MomentumSoftmaxWeight Decay

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