8.3.4.3 Conditional Random Fields, CRF, Segmentation

Stewart, L.[Liam], He, X.M.[Xu-Ming], Zemel, R.S.[Richard S.],
Learning Flexible Features for Conditional Random Fields,
PAMI(30), No. 8, August 2008, pp. 1415-1426.
IEEE DOI 0806
hierarchical models. BibRef

He, X.M.[Xu-Ming], Zemel, R.S.[Richard S.], Ray, D.[Debajyoti],
Learning and Incorporating Top-Down Cues in Image Segmentation,
ECCV06(I: 338-351).
Springer DOI 0608
BibRef

Zhang, L.[Lei], Ji, Q.A.[Qi-Ang],
Image Segmentation with a Unified Graphical Model,
PAMI(32), No. 8, August 2010, pp. 1406-1425.
IEEE DOI 1007
Both causal and noncausal relationships among random variables. Conditional Random Field model, multilayer Bayesian Network. BibRef

Zhang, L.[Lei], Wang, X.[Xun], Penwarden, N.[Nicholas], Ji, Q.A.[Qi-Ang],
An Image Segmentation Framework Based on Patch Segmentation Fusion,
ICPR06(II: 187-190).
IEEE DOI 0609
BibRef

Gai, J.D.[Jia-Ding], Stevenson, R.L.[Robert L.],
Robust contour tracking based on a coupling between geodesic active contours and conditional random fields,
JVCIR(22), No. 1, January 2011, pp. 33-47.
Elsevier DOI 1101
BibRef
Earlier:
Contour tracking based on a synergistic approach of geodesic active contours and conditional random fields,
ICIP10(2801-2804).
IEEE DOI 1009
Contour tracking; 3D conditional random field; Geodesic active contours; Level set methods; Variational inference; Belief propagation; Motion detection; Markov random field BibRef

Zhang, L.[Lei], Ji, Q.A.[Qi-Ang],
A Bayesian Network Model for Automatic and Interactive Image Segmentation,
IP(20), No. 9, September 2011, pp. 2582-2593.
IEEE DOI 1109
BibRef

Zhang, L.[Lei], Ji, Q.A.[Qi-Ang],
A multiscale hybrid model exploiting heterogeneous contextual relationships for image segmentation,
CVPR09(2828-2835).
IEEE DOI 0906
BibRef
Earlier:
Integration of multiple contextual information for image segmentation using a Bayesian Network,
SLAM08(1-6).
IEEE DOI 0806
BibRef

Liu, M.Y.[Ming-Yu], Tuzel, O.[Oncel], Ramalingam, S.[Srikumar], Chellappa, R.[Rama],
Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint,
PAMI(36), No. 1, 2014, pp. 99-112.
IEEE DOI 1312
BibRef
Earlier:
Entropy rate superpixel segmentation,
CVPR11(2097-2104).
IEEE DOI 1106
Clustering. BibRef

Vemulapalli, R., Tuzel, O.[Oncel], Liu, M.Y.[Ming-Yu],
Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising,
CVPR16(4801-4809)
IEEE DOI 1612
BibRef

Vemulapalli, R., Tuzel, O.[Oncel], Liu, M.Y.[Ming-Yu], Chellappa, R.,
Gaussian Conditional Random Field Network for Semantic Segmentation,
CVPR16(3224-3233)
IEEE DOI 1612
BibRef

Wang, L.L.[Li-Li], Yung, N.H.C.[Nelson H. C.],
Improved hierarchical conditional random field model for object segmentation,
MVA(26), No. 7-8, November 2015, pp. 1027-1043.
WWW Link. 1511
BibRef

Liu, F.[Fayao], Lin, G.S.[Guo-Sheng], Shen, C.H.[Chun-Hua],
CRF learning with CNN features for image segmentation,
PR(48), No. 10, 2015, pp. 2983-2992.
Elsevier DOI 1507
Conditional random field (CRF) BibRef

Zand, M., Doraisamy, S., Halin, A.A.[A. Abdul], Mustaffa, M.R.,
Ontology-Based Semantic Image Segmentation Using Mixture Models and Multiple CRFs,
IP(25), No. 7, July 2016, pp. 3233-3248.
IEEE DOI 1606
image segmentation BibRef

Zhu, H.Y.[Hong-Yuan], Lu, J.B.[Jiang-Bo], Cai, J.F.[Jian-Fei], Zheng, J.M.[Jian-Min], Lu, S., Magnenat-Thalmann, N.[Nadia],
Multiple Human Identification and Cosegmentation: A Human-Oriented CRF Approach With Poselets,
MultMed(18), No. 8, August 2016, pp. 1516-1530.
IEEE DOI 1608
BibRef
Earlier: A1, A2, A3, A4, A6, Only:
Poselet-based multiple human identification and cosegmentation,
ICIP14(1076-1080)
IEEE DOI 1502
BibRef
Earlier: A1, A2, A3, A4, A6, Only:
Multiple foreground recognition and cosegmentation: An object-oriented CRF model with robust higher-order potentials,
WACV14(485-492)
IEEE DOI 1406
image capture. Accuracy Image segmentation; Robustness BibRef

Mottaghi, R.[Roozbeh], Fidler, S.[Sanja], Yuille, A.L., Urtasun, R.[Raquel], Parikh, D.[Devi],
Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding,
PAMI(38), No. 1, January 2016, pp. 74-87.
IEEE DOI 1601
Analytical models BibRef

Liu, F.Y.[Fa-Yao], Lin, G.S.[Guo-Sheng], Shen, C.H.[Chun-Hua],
Discriminative Training of Deep Fully Connected Continuous CRFs With Task-Specific Loss,
IP(26), No. 5, May 2017, pp. 2127-2136.
IEEE DOI 1704
Labeling Conditional Random Fields. BibRef

Lin, C.[Chuan], Xu, G.L.[Gui-Li], Cao, Y.J.[Yi-Jun],
Contour detection model using linear and non-linear modulation based on non-CRF suppression,
IET-IPR(12), No. 6, June 2018, pp. 993-1003.
DOI Link 1805
BibRef

Arnab, A.[Anurag], Zheng, S.[Shuai], Jayasumana, S.[Sadeep], Romera-Paredes, B.[Bernardino], Larsson, M., Kirillov, A., Savchynskyy, B., Rother, C., Kahl, F., Torr, P.H.S.[Philip H. S.],
Conditional Random Fields Meet Deep Neural Networks for Semantic Segmentation: Combining Probabilistic Graphical Models with Deep Learning for Structured Prediction,
SPMag(35), No. 1, January 2018, pp. 37-52.
IEEE DOI 1801
Computational modeling, Feature extraction, Image segmentation, Semantics, Visualization BibRef

Brynte, L.[Lucas], Iglesias, J.P.[José Pedro], Olsson, C.[Carl], Kahl, F.[Fredrik],
Learning Structure-From-Motion with Graph Attention Networks,
CVPR24(4808-4817)
IEEE DOI Code:
WWW Link. 2410
Learning systems, Bundle adjustment, Training, Solid modeling, Runtime, Perturbation methods, Structure-from-motion, Equivariance BibRef

Arnab, A.[Anurag], Jayasumana, S.[Sadeep], Zheng, S.[Shuai], Torr, P.H.S.[Philip H. S.],
Higher Order Conditional Random Fields in Deep Neural Networks,
ECCV16(II: 524-540).
Springer DOI 1611
BibRef

Arnab, A.[Anurag], Torr, P.H.S.[Philip H. S.],
Pixelwise Instance Segmentation with a Dynamically Instantiated Network,
CVPR17(879-888)
IEEE DOI 1711
BibRef
Earlier:
Bottom-up Instance Segmentation using Deep Higher-Order CRFs,
BMVC16(xx-yy).
HTML Version. 1805
Detectors, Image segmentation, Object detection, Pipelines, Proposals, Semantics. First, semantic segmentation, then object instance detection. BibRef

Zheng, S.[Shuai], Jayasumana, S.[Sadeep], Romera-Paredes, B.[Bernardino], Vineet, V.[Vibhav], Su, Z.Z.[Zhi-Zhong], Du, D.L.[Da-Long], Huang, C.[Chang], Torr, P.H.S.[Philip H. S.],
Conditional Random Fields as Recurrent Neural Networks,
ICCV15(1529-1537)
IEEE DOI 1602
Combine CNN with CRF. BibRef

Larsson, M.[Måns], Alvén, J.[Jennifer], Kahl, F.[Fredrik],
Max-Margin Learning of Deep Structured Models for Semantic Segmentation,
SCIA17(II: 28-40).
Springer DOI 1706
BibRef

Sultani, W., Mokhtari, S., Yun, H.B.,
Automatic Pavement Object Detection Using Superpixel Segmentation Combined With Conditional Random Field,
ITS(19), No. 7, July 2018, pp. 2076-2085.
IEEE DOI 1807
Feature extraction, Histograms, Image segmentation, Object detection, Shape, Support vector machines, superpixel segmentation BibRef

Chen, L.C.[Liang-Chieh], Papandreou, G.[George], Kokkinos, I.[Iasonas], Murphy, K.P.[Kevin P.], Yuille, A.L.[Alan L.],
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,
PAMI(40), No. 4, April 2018, pp. 834-848.
IEEE DOI 1804
BibRef
Earlier: A2, A1, A4, A5, Only:
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation,
ICCV15(1742-1750)
IEEE DOI 1602
convolution, feature extraction, feedforward neural nets, image segmentation, learning (artificial intelligence), semantic segmentation. Benchmark testing BibRef

Chen, L.C.[Liang-Chieh], Zhu, Y.K.[Yu-Kun], Papandreou, G.[George], Schroff, F.[Florian], Adam, H.[Hartwig],
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation,
ECCV18(VII: 833-851).
Springer DOI 1810
BibRef

Chen, L.C., Barron, J.T., Papandreou, G., Murphy, K.P., Yuille, A.L.,
Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform,
CVPR16(4545-4554)
IEEE DOI 1612
BibRef

Konishi, S.[Scott], Yuille, A.L.,
Statistical Cues for Domain Specific Image Segmentation with Performance Analysis,
CVPR00(I: 125-132).
IEEE DOI 0005
BibRef

He, C.[Chu], Fang, P.Z.[Pei-Zhang], Zhang, Z.[Zhi], Xiong, D.[Dehui], Liao, M.S.[Ming-Sheng],
An End-to-End Conditional Random Fields and Skip-Connected Generative Adversarial Segmentation Network for Remote Sensing Images,
RS(11), No. 13, 2019, pp. xx-yy.
DOI Link 1907
BibRef

Li, Y., Guo, Y., Guo, J., Ma, Z., Kong, X., Liu, Q.,
Joint CRF and Locality-Consistent Dictionary Learning for Semantic Segmentation,
MultMed(21), No. 4, April 2019, pp. 875-886.
IEEE DOI 1903
Dictionaries, Machine learning, Image segmentation, Semantics, Task analysis, Inference algorithms, Shape, locality consistency BibRef

Ma, F.[Fei], Gao, F.[Fei], Sun, J.P.[Jin-Ping], Zhou, H.Y.[Hui-Yu], Hussain, A.[Amir],
Weakly Supervised Segmentation of SAR Imagery Using Superpixel and Hierarchically Adversarial CRF,
RS(11), No. 5, 2019, pp. xx-yy.
DOI Link 1903
BibRef

Joy, T.[Thomas], Desmaison, A.[Alban], Ajanthan, T.[Thalaiyasingam], Bunel, R.[Rudy], Salzmann, M.[Mathieu], Kohli, P.[Pushmeet], Torr, P.H.S.[Philip H. S.], Kumar, M.P.[M. Pawan],
Efficient Relaxations for Dense CRFs with Sparse Higher-Order Potentials,
SIIMS(12), No. 1, 2019, pp. 287-318.
DOI Link 1904
Segmentation and stereo matching. BibRef

Peng, Z.L.[Zi-Li], Li, Q.L.[Qiao-Liang],
Adaptive appearance separation for interactive image segmentation based on Dense CRF,
IET-IPR(13), No. 1, January 2019, pp. 142-151.
DOI Link 1812
BibRef

Zhou, L.[Lei], Kong, X.Y.[Xiang-Yong], Gong, C.[Chen], Zhang, F.[Fan], Zhang, X.G.[Xiao-Guo],
FC-RCCN: Fully convolutional residual continuous CRF network for semantic segmentation,
PRL(130), 2020, pp. 54-63.
Elsevier DOI 2002
Continuous conditional random field (C-CRF), Semantic segmentation, Unary network, Pairwise network BibRef

Berman, M.[Maxim], Blaschko, M.B.[Matthew B.],
Discriminative Training of Conditional Random Fields with Probably Submodular Constraints,
IJCV(128), No. 6, June 2020, pp. 1722-1735.
Springer DOI 2006
BibRef

Zaremba, W.[Wojciech], Blaschko, M.B.[Matthew B.],
Discriminative training of CRF models with probably submodular constraints,
WACV16(1-7)
IEEE DOI 1606
Complexity theory BibRef

Ji, J.[Jian], Shi, R.[Rui], Li, S.T.[Si-Tong], Chen, P.[Peng], Miao, Q.G.[Qi-Guang],
Encoder-Decoder With Cascaded CRFs for Semantic Segmentation,
CirSysVideo(31), No. 5, 2021, pp. 1926-1938.
IEEE DOI 2105
BibRef

Li, Y.J.[Yu-Jie], Sun, J.X.[Jia-Xing], Li, Y.[Yun],
Weakly-Supervised Semantic Segmentation Network With Iterative dCRF,
ITS(23), No. 12, December 2022, pp. 25419-25426.
IEEE DOI 2212
Semantics, Cams, Image segmentation, Convolution, Annotations, Feature extraction, Training, Weakly-supervised, image-level annotations BibRef

Kong, Y.Y.[Ying-Ying], Li, Q.[Qiupeng],
Semantic Segmentation of Polarimetric SAR Image Based on Dual-Channel Multi-Size Fully Connected Convolutional Conditional Random Field,
RS(14), No. 6, 2022, pp. xx-yy.
DOI Link 2204
BibRef

Ma, X.Y.[Xiang-Yue], Xu, J.D.[Jin-Dong], Chong, Q.P.[Qiang-Peng], Ou, S.F.[Shi-Feng], Xing, H.H.[Hai-Hua], Ni, M.Y.[Meng-Ying],
FCUnet: Refined remote sensing image segmentation method based on a fuzzy deep learning conditional random field network,
IET-IPR(17), No. 12, 2023, pp. 3616-3629.
DOI Link 2310
fuzzy logic, image classification, image segmentation, neural nets BibRef

Wan, J.[Jin], Yin, H.[Hui], Wu, Z.Y.[Zhen-Yao], Wu, X.[Xinyi], Liu, Z.H.[Zhi-Hao], Wang, S.[Song],
CRFormer: A cross-region transformer for shadow removal,
IVC(151), 2024, pp. 105273.
Elsevier DOI 2411
Shadow removal, Cross-region transformer, Region-aware cross-attention, One-way interaction BibRef

Carannante, G.[Giuseppina], Bouaynaya, N.C.[Nidhal C.], Dera, D.[Dimah], Fathallah-Shaykh, H.M.[Hassan M.], Rasool, G.[Ghulam],
SUPER-Net: Trustworthy image segmentation via uncertainty propagation in encoder-decoder networks,
PR(172), 2026, pp. 112503.
Elsevier DOI 2512
Bayesian deep learning, Encoder-decoder networks, Reliability, Segmentation, Trustworthiness, Uncertainty estimation BibRef

Zbinden, L.[Lukas], Doorenbos, L.[Lars], Pissas, T.[Theodoros], Huber, A.T.[Adrian Thomas], Sznitman, R.[Raphael], Márquez-Neila, P.[Pablo],
Stochastic Segmentation with Conditional Categorical Diffusion Models,
ICCV23(1119-1129)
IEEE DOI 2401
BibRef

Li, W.H.[Wei-Hao], Yang, M.Y.[Michael Ying],
Efficient Semantic Segmentation Of Man-made Scenes Using Fully-connected Conditional Random Field,
ISPRS16(B3: 633-640).
DOI Link 1610
BibRef

Sulimowicz, L., Ahmad, I., Aved, A.,
Superpixel-Enhanced Pairwise Conditional Random Field for Semantic Segmentation,
ICIP18(271-275)
IEEE DOI 1809
Image segmentation, Semantics, Kernel, Labeling, Robustness, Visualization, Image color analysis, and Higher-order CRFs BibRef

Shen, F., Gan, R., Yan, S., Zeng, G.,
Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF,
CVPR17(5178-5186)
IEEE DOI 1711
Complexity theory, Image segmentation, Message passing, Predictive models, Semantics, Training BibRef

Zhou, H., Zhang, J.[Jun], Lei, J.[Jun], Li, S.[Shuohao], Tu, D.[Dan],
Image semantic segmentation based on FCN-CRF model,
ICIVC16(9-14)
IEEE DOI 1610
feature extraction BibRef

Hayder, Z.[Zeeshan], He, X.M.[Xu-Ming], Salzmann, M.[Mathieu],
Structural Kernel Learning for Large Scale Multiclass Object Co-detection,
ICCV15(2632-2640)
IEEE DOI 1602
BibRef
Earlier: A1, A3, A2:
Object Co-detection via Efficient Inference in a Fully-Connected CRF,
ECCV14(III: 330-345).
Springer DOI 1408
BibRef

Kolesnikov, A.[Alexander], Guillaumin, M.[Matthieu], Ferrari, V.[Vittorio], Lampert, C.H.[Christoph H.],
Closed-Form Approximate CRF Training for Scalable Image Segmentation,
ECCV14(III: 550-565).
Springer DOI 1408
BibRef

Kae, A.[Andrew], Marlin, B.M.[Benjamin M>], Learned-Miller, E.G.[Erik G.],
The Shape-Time Random Field for Semantic Video Labeling,
CVPR14(272-279)
IEEE DOI 1409
CRF; RBM; deep learning; deep model; faces; image labeling BibRef

Kae, A.[Andrew], Sohn, K.[Kihyuk], Lee, H.L.[Hong-Lak], Learned-Miller, E.G.[Erik G.],
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling,
CVPR13(2019-2026)
IEEE DOI 1309
attributes; deep learning; face processing; segmentation BibRef

Roig, G.[Gemma], Boix, X.[Xavier], de Nijs, R.[Roderick], Ramos, S.[Sebastian], Kuhnlenz, K.[Koljia], Van Gool, L.J.[Luc J.],
Active MAP Inference in CRFs for Efficient Semantic Segmentation,
ICCV13(2312-2319)
IEEE DOI 1403
using expensive features. BibRef

Mottaghi, R.[Roozbeh], Fidler, S.[Sanja], Yao, J.[Jian], Urtasun, R.[Raquel], Parikh, D.[Devi],
Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs,
CVPR13(3143-3150)
IEEE DOI 1309
Explore effects by using humans in loop for parts of the problem. BibRef

Zhang, H.H.[Hong-Hui], Wang, J.D.[Jing-Dong], Tan, P.[Ping], Wang, J.L.[Jing-Lu], Quan, L.[Long],
Learning CRFs for Image Parsing with Adaptive Subgradient Descent,
ICCV13(3080-3087)
IEEE DOI 1403
Adaptive Subgradient Descent; Conditional Random Field; Image Parsing BibRef

Zhou, L.[Lei], Qiao, Y.[Yu], Yang, J.[Jie], p He, X.J.[Xiang-Jian],
Learning geodesic CRF model for image segmentation,
ICIP12(1565-1568).
IEEE DOI 1302
BibRef

Moayedi, F., Azimifar, Z., Fieguth, P.W., Kazemi, A.,
Adaptive multi-resolution CRF-based contour tracking,
ICIP11(497-500).
IEEE DOI 1201
BibRef

Xue, F.[Fei], Zhang, Y.J.[Yu-Jin],
Image Class Segmentation via Conditional Random Field over Weighted Histogram Classifier,
ICIG11(477-481).
IEEE DOI 1109
BibRef

Besbes, O.[Olfa], Boujemaa, N.[Nozha], Belhadj, Z.[Ziad],
Embedding Gestalt Laws on Conditional Random Field for Image Segmentation,
ISVC11(I: 236-245).
Springer DOI 1109
BibRef
Earlier:
Stochastic image segmentation by combining region and edge cues,
ICIP08(2288-2291).
IEEE DOI 0810
BibRef
Earlier: A1, A3, A2:
A Variational Framework for Adaptive Satellite Images Segmentation,
SSVM07(675-686).
Springer DOI 0705
BibRef
And: A1, A3, A2:
Adaptive Satellite Images Segmentation by Level Set Multiregion Competition,
INRIARR-5855, 2006.
HTML Version. BibRef

Yang, W.[Wen], Dai, D.X.[Deng-Xin], Triggs, B.[Bill], Xia, G.S.[Gui-Song], He, C.[Chu],
Fast semantic scene segmentation with conditional random field,
ICIP10(229-232).
IEEE DOI 1009
BibRef

Cobzas, D.[Dana], Schmidt, M.[Mark],
Increased discrimination in level set methods with embedded conditional random fields,
CVPR09(328-335).
IEEE DOI 0906
Improve level set segmentation by embedding trained conditional random field into energy function. BibRef

Wu, X.Q.[Xu-Qing], Shah, S.K.[Shishir K.],
Level Set with Embedded Conditional Random Fields and Shape Priors for Segmentation of Overlapping Objects,
ACCV10(II: 230-241).
Springer DOI 1011
BibRef

Warrell, J.[Jonathan], Moore, A.P.[Alastair P.], Prince, S.J.D.[Simon J.D.],
Vistas: Hierarchial boundary priors using multiscale conditional random fields,
BMVC09(xx-yy).
PDF File. 0909
BibRef

Chapter on 2-D Region Segmentation Techniques, Snakes, Active Contours continues in
Neural Networks for Segmentation .