Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks
Open accessAbstract
Contextual information plays an important role in solving vision problems such as image segmentation. However, extracting contextual information and using it in an effective way remains a difficult problem. To address this challenge, we propose a multi-resolution contextual framework, called cascaded hierarchical model (CHM), which learns contextual information in a hierarchical framework for image segmentation. At each level of the hierarchy, a classifier is trained based on downsampled input images and outputs of previous levels. Our model then incorporates the resulting multi-resolution contextual information into a classifier to segment the input image at original resolution. We repeat this procedure by cascading the hierarchical framework to improve the segmentation accuracy. Multiple classifiers are learned in the CHM; therefore, a fast and accurate classifier is required to make the training tractable. The classifier also needs to be robust against overfitting due to the large number of parameters learned during training. We introduce a novel classification scheme, called logistic disjunctive normal networks (LDNN), which consists of one adaptive layer of feature detectors implemented by logistic sigmoid functions followed by two fixed layers of logical units that compute conjunctions and disjunctions, respectively. We demonstrate that LDNN outperforms state-of-theart classifiers and can be used in the CHM to improve object segmentation performance.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · see citing works
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · see citing works
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 24,190 · see citing works
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · see citing works
Improving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382 · see citing works
Medical image analysis: progress over two decades and the challenges ahead
Duncan, J. S., & Ayache, N. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.824822 · Cited by 4,167 · see citing works
The Cascade-Correlation learning architecture
Fahlman, S. E., & Lebiere, C. J. (2018) · doi:10.1184/r1/6610403 · Cited by 2,391 · see citing works
SIFT Flow: Dense Correspondence across Scenes and Its Applications
Liu, C., Yuen, J., & Torralba, A. B. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.147 · Cited by 1,590 · see citing works
Shotton, J., Winn, J. M., Rother, C., & Criminisi, A. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-007-0109-1 · Cited by 1,014 · see citing works
Multiscale conditional random fields for image labeling
He, X., Zemel, R. S., & Carreira-Perpiñán, M. Á. (2004) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2004.1315232 · Cited by 843 · see citing works
Fuzzy min-max neural networks. I. Classification
Simpson, P. K. (1992) · IEEE Transactions on Neural Networks · doi:10.1109/72.159066 · Cited by 781 · see citing works
Auto-Context and Its Application to High-Level Vision Tasks and 3D Brain Image Segmentation
Tu, Z., & Bai, X. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.186 · Cited by 578 · see citing works
From contours to regions: An empirical evaluation
Arbeláez, P., Maire, M., Fowlkes, C. C., & Malik, J. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206707 · Cited by 447 · see citing works
Supervised Learning of Edges and Object Boundaries
Dollár, P., Zhuowen Tu, A., & Belongie, S. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.298 · Cited by 428 · see citing works
(1995) · Springer eBooks · doi:10.1007/978-1-4899-3791-9 · Cited by 391 · see citing works
Contextual models for object detection using boosted random fields
Torralba, A. B., Murphy, K. P., & Freeman, W. T. (2004) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 303 · see citing works
Discriminative models for multi-class object layout
Desai, C., Ramanan, D., & Fowlkes, C. C. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459256 · Cited by 281 · see citing works
Combining Top-Down and Bottom-Up Segmentation
Borenstein, E., Sharon, E., & Ullman, S. (2005) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvpr.2004.314 · Cited by 273 · see citing works
Simpson, P. K. (1991) · IEEE International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1991.170647 · Cited by 177 · see citing works
Learning to Combine Bottom-Up and Top-Down Segmentation
Levin, A., & Weiss, Y. (2006) · Lecture notes in computer science · doi:10.1007/11744085_45 · Cited by 165 · see citing works
Cascaded Classification Models: Combining Models for Holistic Scene Understanding
Heitz, G., Gould, S. J., Saxena, A., & Koller, D. (2008) · Cited by 152 · see citing works
A Tree-Based Context Model for Object Recognition
Choi, M. J., Torralba, A. B., & Willsky, A. S. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.119 · Cited by 145 · see citing works
Figure-ground segmentation by transferring window masks
Kuettel, D., & Ferrari, V. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247721 · Cited by 110 · see citing works
Kernelized structural SVM learning for supervised object segmentation
Bertelli, L., Yu, T., Vu, D., & Gokturk, S. B. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995597 · Cited by 100 · see citing works
Jurrus, E. R., Paiva, A. R. C., Watanabe, S., et al. (2010) · Medical Image Analysis · doi:10.1016/j.media.2010.06.002 · Cited by 95 · see citing works
Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models
Li, C., Kowdle, A., Saxena, A., & Chen, T. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.232 · Cited by 90 · see citing works
Radon-Like features and their application to connectomics
Kumar, R., Vázquez-Reina, A., & Pfister, H. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543594 · Cited by 74 · see citing works
Encyclopaedia of Mathematics, Supplement III
Abhyankar, S. S., Абрамов, В. О., Ádem, A., et al. (2002) · Springer eBooks · doi:10.1007/978-0-306-48373-8 · Cited by 72 · see citing works
Lucanus, L. M. A. (1993) · Oxford University Press eBooks · doi:10.1093/oseo/instance.00077057 · Cited by 41 · see citing works
Seyedhosseini, M., Kumar, R., Jurrus, E. R., Giuly, R., Ellisman, M. H., Pfister, H., & Taşdizen, T. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23623-5_84 · Cited by 33 · see citing works
Self-citationA neural network classifier with disjunctive fuzzy information
Lee, H.-M., Chen, K.-H., & Jiang, I.-F. (1998) · Neural Networks · doi:10.1016/s0893-6080(98)00058-6 · Cited by 31 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · see citing works
“More recent approaches [11,4] proposed a classifier output that takes into account the features from multiple layers.”
Background3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_49 · Cited by 7,945 · see citing works
- Authors
- Seyedhosseini, M., Sajjadi, M., & Tasdizen, T.
- Affiliations
- University of Utah (US)
- Venue
- 2013 IEEE International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2013-12
- Volume
- 2013
- Pages
- 2168-2175
- PMC
- PMC4240525
- OpenAlex
- W2106146968
- Cited by
- 95
- References
- 31
- Citations by year
- 2026: 2 · 2025: 4 · 2024: 4 · 2023: 7 · 2022: 9 · 2021: 9 · 2020: 11 · 2019: 11 · 2018: 7 · 2017: 3 · 2016: 8 · 2015: 13 · 2014: 7
- FWCI
- 5.96
- Type
- conference paper
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Institutes of Health
- National Institute of Neurological Disorders and Stroke (R01NS075314)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- image segmentation, contextual information, multi-resolution feature extraction, hierarchical classification, object segmentation, feature detectors, overfitting robustness
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
