Fully convolutional networks for semantic segmentation
The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.
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, 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Dense training on a whole volume was inapplicable in these experimental settings due to memory limitations but was previously shown to give similar results as training on uniformly sampled patches( Long et al., 2015 ).”
From Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation (2017) · cites this paper as Long et al., 2015
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The fully CNN with an encoder-decoder structure has become the de facto paradigm for semantic segmentation [75], [76], since it can learn discriminative and multi-resolution features through cascaded convolution blocks while preserving spatial correspondence.”
From Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things (2021) · cites this paper as [76]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The first approach to showcase the deep learning potential on this task is found in [14], which introduced an end-to-end convolutional model, the so-called Fully Convolutional Network (FCN) model, which is made of an encoder (or contraction segment) and a decoder (or expansion segment).”
From Multimodal semantic segmentation in autonomous driving: A review of current approaches and future perspectives (2022) · cites this paper as [14]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Therefore, semantic-wise architectures produce results for each pixel/voxel of an image much faster than patch-wise architectures.”
From Deep learning for brain MRI segmentation: state of the art and future directions (2017) · cites this paper as [60]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Facilitated by deep CNNs, especially by the end-to-end fully convolutional network (FCN) (Long et al., 2015), interest in semantic segmentation of remote sensing images has increased in recent years.”
From Deep learning in remote sensing applications: A meta-analysis and review (2019) · cites this paper as Long et al., 2015
8 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Self-citationBook Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
A Wavelet Tour of Signal Processing
(1999) · Elsevier eBooks · doi:10.1016/b978-0-12-466606-1.x5000-4 · Cited by 16,227
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Self-citation
Research works printed but not linked: 5
- [39] N. Zhang, J. Donahue, R. Girshick, and T. Darrell. Partbased r-cnns for fine-grained category detection. In Computer Vision-ECCV 2014 , pages 834-849. Springer, 2014. 1
- giusti, 2013, ICIP
- [10] L. Florack, B. T. H. Romeny, M. Viergever, and J. Koenderink. The gaussian scale-space paradigm and the multiscale local jet. International Journal of Computer Vision , 18(1):61-75, 1996. 5 -
- [20] Q. V. Le, R. Monga, M. Devin, K. Chen, G. S. Corrado, J. Dean, and A. Y. Ng. Building high-level features using large scale unsupervised learning. In ICML , 2012. 3 -
- [25] O. Matan, C. J. Burges, Y. LeCun, and J. S. Denker. Multidigit recognition using a space displacement neural network. In NIPS , pages 488-495. Citeseer, 1991. 2 -
Cited by
Items 1,801–1,819 of 1,819
Pixel Level Image Encryption Based on Semantic Segmentation
Shan, Y., He, M., Yu, Z., & Wu, H. (2018) · 2018 International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO) · doi:10.1109/iccairo.2018.00032 · Cited by 7
Playing the System: Can Puzzle Players Teach us How to Solve Hard Problems?
Mutalova, R., Sarrazin-Gendron, R., Cai, E., Richard, G., Ghasemloo Gheidari, P., Caisse, S., Knight, R., Blanchette, M., Szantner, A., & Waldispühl, J. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581375 · Cited by 6
An Efficient Object Detection Algorithm Based on Compressed Networks
Li, J., Peng, K., & Chang, C.-C. (2018) · Symmetry · doi:10.3390/sym10070235 · Cited by 6
Robust and Real-Time Face Swapping Based on Face Segmentation and CANDIDE-3
Wang, H., Xie, D., & Wei, L. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-97310-4_38 · Cited by 6
Zhu, M., Zecchin, M., Park, S., Guo, C., Feng, C., Popovski, P., & Simeone, O. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3549222 · Cited by 6
Elucidating image-to-set prediction: An analysis of models, losses and datasets
Pineda, L., Salvador, A., Drozdzal, M., & Romero, A. (2019) · arXiv · doi:10.48550/arxiv.1904.05709 · Cited by 6
A central multimodal fusion framework for outdoor scene image segmentation
Zhang, Y., Morel, O., Seulin, R., Mériaudeau, F., & Sidibé, D. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10357-y · Cited by 5
Qiu, Y., Lu, H., Mei, J., Bao, S., & Xu, J. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124734 · Cited by 5
Exploring Sensor Impact and Architectural Robustness in Adverse Weather on BEV Perception
Kumar, S., Sharma, S., Asghar, R., Mohandas, R., Brophy, T., Sistu, G., Grua, E. M., Donzella, V., & Eising, C. (2025) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2025.3621862 · Cited by 5
“Uricar et al. introduced the Desoiling Dataset [43] with paired clean and soiled fisheye videos, and applied CycleGAN-based [44] restoration to improve segmentation using ResNet50 [45] and FCN8 [46].”
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., & Zomaya, A. Y. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3120998 · Cited by 5
Fernández, J., Bornn, L., & Cervone, D. (2021) · Machine Learning · doi:10.1007/s10994-021-05989-6 · Cited by 5
BDCN: Semantic Embedding Self-explanatory Breast Diagnostic Capsules Network
Chen, D., Zhong, K., & He, J. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-84186-7_28 · Cited by 3
Human-inspired Perspectives: A Survey on AI Long-term Memory
He, Z., Lin, W., Zheng, H., Zhang, F., Jones, M. W., Aitchison, L., Xu, X., Liu, M., Kristensson, P. O., & Shen, J. (2024) · arXiv · doi:10.48550/arxiv.2411.00489 · Cited by 3
Zhang, S., Lin, W., Li, Z., Jiang, R., Liang, C., Fan, M., & Masu, R. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675623 · Cited by 3
Emotion Prediction from User-Generated Videos by Emotion Wheel Guided Deep Learning
Ho, C.-T., Lin, Y.-H., & Wu, J.-L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46687-3_1 · Cited by 2
Median Filter Helps Lymph Node Segmentation in Deep Learning via PET/CT
Zhang, X., Liao, W., & Xu, G. (2021) · 2021 4th International Conference on Digital Medicine and Image Processing · doi:10.1145/3506651.3506662 · Cited by 1
Multi-stage Floor Plan Recognition and 3D Reconstruction
Cheng, X., Ding, X., Zhang, J., Liu, M., Chang, K., Wang, J., Zhou, C., & Yuan, J. (2022) · Proceedings of the 8th International Conference on Computing and Artificial Intelligence · doi:10.1145/3532213.3532271 · Cited by 1
Thota, A., Sri, N. D., Dinesh, K., & Prasannatha, A. (2026) · 2026 9th International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei68323.2026.11542103
rNCA: Self-Repairing Segmentation Masks
Silbernagel, M., Alonso, A., Petersen, J., Ibragimov, B., de Bruijne, M., & Wyburd, M. K. (2025) · arXiv · doi:10.48550/arxiv.2512.13397
“Modern segmentation networks achieve strong pixel-and voxel-level accuracy across medical tasks, but often fail to preserve topological correctness when dealing with thin branches, closures, and continuity [1–5].”
Metadata
- Authors
- Long, J., Shelhamer, E., & Darrell, T.
- Affiliations
- University of California, Berkeley (US)
- Venue
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2015-06
- Pages
- 3431-3440
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1903029394
- Semantic Scholar
- 6fc6803df5f9ae505cae5b2f178ade4062c768d0
- Cited by
- 38,834
- References
- 49
- Citations by year
- 2026: 1770 · 2025: 3611 · 2024: 4505 · 2023: 4711 · 2022: 4731 · 2021: 5072 · 2020: 4612 · 2019: 4342 · 2018: 2860 · 2017: 1743 · 2016: 742 · 2015: 127
- FWCI
- 748.24
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Funders
- Nvidia
- Defense Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Keywords
- fully convolutional network, semantic segmentation, skip connections, fine-tuning, transfer learning, AlexNet, VGG, GoogLeNet, inference efficiency, Pascal VOC, SIFT flow
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.