Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
149 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Learning Topological Representations for Deep Image Understanding (2403.15361v1)

Published 22 Mar 2024 in cs.CV and cs.LG

Abstract: In many scenarios, especially biomedical applications, the correct delineation of complex fine-scaled structures such as neurons, tissues, and vessels is critical for downstream analysis. Despite the strong predictive power of deep learning methods, they do not provide a satisfactory representation of these structures, thus creating significant barriers in scalable annotation and downstream analysis. In this dissertation, we tackle such challenges by proposing novel representations of these topological structures in a deep learning framework. We leverage the mathematical tools from topological data analysis, i.e., persistent homology and discrete Morse theory, to develop principled methods for better segmentation and uncertainty estimation, which will become powerful tools for scalable annotation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (227)
  1. Deep models for brain em image segmentation: novel insights and improved performance. Bioinformatics, 2016.
  2. Topology-preserving deep image segmentation. In Advances in neural information processing systems (NeurIPS), 2019.
  3. Neural cleanse: Identifying and mitigating backdoor attacks in neural networks. In IEEE Symposium on Security and Privacy (SP), 2019.
  4. Abs: Scanning neural networks for back-doors by artificial brain stimulation. In ACM SIGSAC Conference on Computer and Communications Security, 2019.
  5. Tabor: A highly accurate approach to inspecting and restoring trojan backdoors in ai systems. In International Conference on Data Mining (ICDM), 2019.
  6. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015.
  7. A probabilistic u-net for segmentation of ambiguous images. In Advances in neural information processing systems (NeurIPS), 2018.
  8. Topology-aware segmentation using discrete morse theory. In International Conference on Learning Representations (ICLR), 2021.
  9. Learning probabilistic topological representations using discrete morse theory. In International Conference on Learning Representations (ICLR), 2023.
  10. Fully convolutional networks for semantic segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2015.
  11. Mask r-cnn. In International Conference on Computer Vision (ICCV), 2017.
  12. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062, 2014.
  13. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018.
  14. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587, 2017.
  15. Train faster, generalize better: Stability of stochastic gradient descent. In International Conference on Machine Learning (ICML), 2016.
  16. John Milnor. Morse theory.(AM-51). Princeton university press, 1963.
  17. Robin Forman. A user’s guide to discrete morse theory. Sém. Lothar. Combin, 2002.
  18. Serguei Barannikov. The framed morse complex and its invariants. American Mathematical Society Translations, Series 2, 1994.
  19. Computational topology: an introduction. American Mathematical Soc., 2010.
  20. Topological persistence and simplification. In IEEE Symposium on Foundations of Computer Science (FOCS), 2000.
  21. The structure and stability of persistence modules. arXiv preprint arXiv:1207.3674, 2012.
  22. Confidence sets for persistence diagrams. The Annals of Statistics, 2014.
  23. Persistence barcodes for shapes. International Journal of Shape Modeling, 2005.
  24. A general neural network architecture for persistence diagrams and graph classification. arXiv preprint arXiv:1904.09378, 2019.
  25. Azriel Rosenfeld. Digital topology. The American Mathematical Monthly, 1979.
  26. Optimal topological cycles and their application in cardiac trabeculae restoration. In Information Processing in Medical Imaging (IPMI), 2017.
  27. Statistical topological data analysis-a kernel perspective. In Advances in neural information processing systems (NeurIPS), 2015.
  28. Kernel partial least squares regression for relating functional brain network topology to clinical measures of behavior. In International Symposium on Biomedical Imaging (ISBI), 2016.
  29. Persistence-based clustering in riemannian manifolds. Journal of the ACM (JACM), 2013.
  30. Composing tree graphical models with persistent homology features for clustering mixed-type data. In International Conference on Machine Learning (ICML), 2017.
  31. Persistence images: A stable vector representation of persistent homology. Journal of Machine Learning Research (JMLR), 2017.
  32. Peter Bubenik. Statistical topological data analysis using persistence landscapes. Journal of Machine Learning Research (JMLR), 2015.
  33. Persistent topology of decision boundaries. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2015.
  34. Persistence enhanced graph neural network. In Artificial Intelligence and Statistics Conference (AISTATS), 2020.
  35. Link prediction with persistent homology: An interactive view. In International Conference on Machine Learning (ICML), 2021.
  36. A topological filter for learning with label noise. In Advances in neural information processing systems (NeurIPS), 2020.
  37. Ventricular blood flow analysis using topological methods. In International Symposium on Biomedical Imaging (ISBI), 2015.
  38. The structure and stability of persistence modules. Springer, 2016.
  39. A topological loss function for deep-learning based image segmentation using persistent homology. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020.
  40. Localization in the crowd with topological constraints. In AAAI Conference on Artificial Intelligence (AAAI), 2021.
  41. Topogan: A topology-aware generative adversarial network. In European Conference on Computer Vision (ECCV), 2020.
  42. Connectivity-optimized representation learning via persistent homology. In International Conference on Machine Learning (ICML), 2019.
  43. Graph filtration learning. In International Conference on Machine Learning (ICML), 2020.
  44. Perslay: A neural network layer for persistence diagrams and new graph topological signatures. In Artificial Intelligence and Statistics Conference (AISTATS), 2020.
  45. A topological regularizer for classifiers via persistent homology. In Artificial Intelligence and Statistics Conference (AISTATS), 2019.
  46. Efficient piecewise training of deep structured models for semantic segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2016.
  47. A structured self-attentive sentence embedding. In International Conference on Learning Representations (ICLR), 2017.
  48. Disan: Directional self-attention network for rnn/cnn-free language understanding. In AAAI Conference on Artificial Intelligence (AAAI), 2018.
  49. Attention is all you need. In Advances in neural information processing systems (NeurIPS), 2017.
  50. Self-attention generative adversarial networks. In International Conference on Machine Learning (ICML), 2019.
  51. Non-local neural networks. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2018.
  52. Psanet: Point-wise spatial attention network for scene parsing. In European Conference on Computer Vision (ECCV), 2018.
  53. Learning deconvolution network for semantic segmentation. In International Conference on Computer Vision (ICCV), 2015.
  54. Deep neural networks segment neuronal membranes in electron microscopy images. In Advances in neural information processing systems (NeurIPS), 2012.
  55. Large scale image segmentation with structured loss based deep learning for connectome reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018.
  56. Pointrend: Image segmentation as rendering. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2020.
  57. Multi-stage multi-recursive-input fully convolutional networks for neuronal boundary detection. In International Conference on Computer Vision (ICCV), 2017.
  58. Scene segmentation with dag-recurrent neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
  59. Supervised learning of edges and object boundaries. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2006.
  60. Using contours to detect and localize junctions in natural images. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2008.
  61. Spectral segmentation with multiscale graph decomposition. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2005.
  62. Learning hierarchical features for scene labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2012.
  63. Recurrent convolutional neural networks for scene labeling. In International Conference on Machine Learning (ICML), 2014.
  64. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In International Conference on 3D Vision (3DV), 2016.
  65. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, 2017.
  66. Region mutual information loss for semantic segmentation. In Advances in neural information processing systems (NeurIPS), 2019.
  67. Learning hierarchical features for scene labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2013.
  68. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 2021.
  69. Globally optimal segmentation of multi-region objects. In International Conference on Computer Vision (ICCV), 2009.
  70. Higher-order segmentation via multicuts. Computer Vision and Image Understanding (CVIU), 2016.
  71. Masklab: Instance segmentation by refining object detection with semantic and direction features. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2018.
  72. Instance-sensitive fully convolutional networks. In European Conference on Computer Vision (ECCV), 2016.
  73. Fully convolutional instance-aware semantic segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2017.
  74. Mask scoring r-cnn. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2019.
  75. Path aggregation network for instance segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2018.
  76. Instancecut: from edges to instances with multicut. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2017.
  77. Deep watershed transform for instance segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2017.
  78. Proposal-free network for instance-level object segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
  79. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (NeurIPS), 2012.
  80. Combining fully convolutional and recurrent neural networks for 3d biomedical image segmentation. In Advances in neural information processing systems (NeurIPS), 2016.
  81. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  82. Deep residual learning for image recognition. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2016.
  83. Going deeper with convolutions. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2015.
  84. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.
  85. Boundary-aware feature propagation for scene segmentation. In International Conference on Computer Vision (ICCV), 2019.
  86. Boundary loss for highly unbalanced segmentation. In Medical Imaging with Deep Learning (MIDL), 2019.
  87. Reducing the hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Transactions on Medical Imaging (TMI), 2020.
  88. Topology-preserving image segmentation by beltrami representation of shapes. Journal of Mathematical Imaging and Vision, 2018.
  89. Shape-aware organ segmentation by predicting signed distance maps. arXiv preprint arXiv:1912.03849, 2019.
  90. Learning active contour models for medical image segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2019.
  91. Topology aware fully convolutional networks for histology gland segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016.
  92. Brain tumor segmentation using topological loss in convolutional networks. In International Conference on Medical Imaging with Deep Learning–Extended Abstract Track, 2019.
  93. Image analysis using mathematical morphology. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 1987.
  94. Beyond the pixel-wise loss for topology-aware delineation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2018.
  95. A topology preserving level set method for geometric deformable models. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2003.
  96. Self-repelling snakes for topology-preserving segmentation models. IEEE Transactions on Image Processing (TIP), 2008.
  97. Global regularizing flows with topology preservation for active contours and polygons. IEEE Transactions on Image Processing (TIP), 2007.
  98. Florent Ségonne. Active contours under topology control—genus preserving level sets. International Journal of Computer Vision (IJCV), 2008.
  99. Segmenting the papillary muscles and the trabeculae from high resolution cardiac ct through restoration of topological handles. In Information Processing in Medical Imaging (IPMI), 2013.
  100. Graph cut based image segmentation with connectivity priors. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2008.
  101. Global connectivity potentials for random field models. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2009.
  102. Topology cuts: A novel min-cut/max-flow algorithm for topology preserving segmentation in n–d images. Computer Vision and Image Understanding (CVIU), 2008.
  103. Enforcing topological constraints in random field image segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2011.
  104. Probabilistic image segmentation with closedness constraints. In International Conference on Computer Vision (ICCV), 2011.
  105. Tree shape priors with connectivity constraints using convex relaxation on general graphs. In International Conference on Computer Vision (ICCV), 2013.
  106. Generalized connectivity constraints for spatio-temporal 3d reconstruction. In European Conference on Computer Vision (ECCV), 2014.
  107. Tree topology estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014.
  108. Maximin affinity learning of image segmentation. In Advances in neural information processing systems (NeurIPS), 2009.
  109. cldice-a novel topology-preserving loss function for tubular structure segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2021.
  110. A stable multi-scale kernel for topological machine learning. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2015.
  111. Persistence weighted gaussian kernel for topological data analysis. In International Conference on Machine Learning (ICML), 2016.
  112. Sliced wasserstein kernel for persistence diagrams. In International Conference on Machine Learning (ICML), 2017.
  113. Clustering high dimensional categorical data via topographical features. In International Conference on Machine Learning (ICML), 2016.
  114. Topology noise removal for curve and surface evolution. In International MICCAI Workshop on Medical Computer Vision, 2010.
  115. Proximity of persistence modules and their diagrams. In Symposium on Computational Geometry (SoCG), 2009.
  116. Topological function optimization for continuous shape matching. In Computer Graphics Forum, 2018.
  117. Deep learning with topological signatures. In Advances in neural information processing systems (NeurIPS), 2017.
  118. Skeletonization and partitioning of digital images using discrete morse theory. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014.
  119. Theory and algorithms for constructing discrete morse complexes from grayscale digital images. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2011.
  120. Efficient map reconstruction and augmentation via topological methods. In ACM SIGSPATIAL, 2015.
  121. Road network reconstruction from satellite images with machine learning supported by topological methods. In ACM SIGSPATIAL Intl. Conf. Adv. Geographic Information Systems (GIS), 2019.
  122. Semantic segmentation of microscopic neuroanatomical data by combining topological priors with encoder–decoder deep networks. Nature Machine Intelligence, 2020.
  123. High-precision automated reconstruction of neurons with flood-filling networks. Nature methods, 2018.
  124. An efficient conditional random field approach for automatic and interactive neuron segmentation. Medical Image Analysis (MedIA), 2016.
  125. Diverse multiple prediction on neuron image reconstruction. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2019.
  126. On the need for topology-aware generative models for manifold-based defenses. In International Conference on Learning Representations (ICLR), 2020.
  127. Badnets: Identifying vulnerabilities in the machine learning model supply chain. arXiv preprint arXiv:1708.06733, 2017.
  128. Cassandra: Detecting trojaned networks from adversarial perturbations. arXiv preprint arXiv:2007.14433, 2020.
  129. Adversarial examples in the physical world, 2016.
  130. Intriguing properties of neural networks. In International Conference on Learning Representations (ICLR), 2013.
  131. Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526, 2017.
  132. Revealing backdoors, post-training, in dnn classifiers via novel inference on optimized perturbations inducing group misclassification. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020.
  133. Fine-pruning: Defending against backdooring attacks on deep neural networks. In International Symposium on Research in Attacks, Intrusions, and Defenses, 2018.
  134. Baseline pruning-based approach to trojan detection in neural networks. arXiv preprint arXiv:2101.12016, 2021.
  135. Sentinet: Detecting localized universal attacks against deep learning systems. In IEEE Security and Privacy Workshops (SPW), 2020.
  136. Strip: A defence against trojan attacks on deep neural networks. In Annual Computer Security Applications Conference, 2019.
  137. Neural trojans. In IEEE International Conference on Computer Design (ICCD), 2017.
  138. Nic: Detecting adversarial samples with neural network invariant checking. In Network and Distributed System Security (NDSS), 2019.
  139. Detecting backdoor attacks on deep neural networks by activation clustering. In SafeAI@ AAAI, 2019.
  140. Backdoor scanning for deep neural networks through k-arm optimization. In International Conference on Machine Learning (ICML), 2021.
  141. Poisoned classifiers are not only backdoored, they are fundamentally broken. arXiv preprint arXiv:2010.09080, 2020.
  142. Spectral signatures in backdoor attacks. In Advances in neural information processing systems (NeurIPS), 2018.
  143. Deepinspect: A black-box trojan detection and mitigation framework for deep neural networks. In International Joint Conference on Artificial Intelligence (IJCAI), 2019.
  144. Universal litmus patterns: Revealing backdoor attacks in cnns. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2020.
  145. Practical detection of trojan neural networks: Data-limited and data-free cases. In European Conference on Computer Vision (ECCV), 2020.
  146. Top: Backdoor detection in neural networks via transferability of perturbation. arXiv preprint arXiv:2103.10274, 2021.
  147. Topological detection of trojaned neural networks. In Advances in neural information processing systems (NeurIPS), 2021.
  148. Alex Graves. Practical variational inference for neural networks. In Advances in neural information processing systems (NeurIPS), 2011.
  149. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In International Conference on Machine Learning (ICML), 2016.
  150. Simple and scalable predictive uncertainty estimation using deep ensembles. In Advances in neural information processing systems (NeurIPS), 2017.
  151. Confidence-aware learning for deep neural networks. In International Conference on Machine Learning (ICML), 2020.
  152. Multiple choice learning: Learning to produce multiple structured outputs. In Advances in neural information processing systems (NeurIPS), 2012.
  153. Why m heads are better than one: Training a diverse ensemble of deep networks. arXiv preprint arXiv:1511.06314, 2015.
  154. Stochastic multiple choice learning for training diverse deep ensembles. In Advances in neural information processing systems (NeurIPS), 2016.
  155. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2015.
  156. Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680, 2015.
  157. What uncertainties do we need in bayesian deep learning for computer vision? In Advances in neural information processing systems (NeurIPS), 2017.
  158. Learning in an uncertain world: Representing ambiguity through multiple hypotheses. In International Conference on Computer Vision (ICCV), 2017.
  159. Uncertainty estimates and multi-hypotheses networks for optical flow. In European Conference on Computer Vision (ECCV), 2018.
  160. Computing persistent homology. Discrete & Computational Geometry, 2005.
  161. James R Munkres. Elements of algebraic topology. CRC press, 2018.
  162. Persistent homology computation with a twist. In European Workshop on Computational Geometry, 2011.
  163. Efficient computation of persistent homology for cubical data. In Topological methods in data analysis and visualization II. Springer, 2012.
  164. Lipschitz functions have l p-stable persistence. Foundations of computational mathematics, 2010.
  165. Facundo Mémoli. Gromov–wasserstein distances and the metric approach to object matching. Foundations of computational mathematics, 2011.
  166. Geometry helps to compare persistence diagrams. Journal of Experimental Algorithmics (JEA), 2017.
  167. Stability of persistence diagrams. Discrete & Computational Geometry, 2007.
  168. Crowdsourcing the creation of image segmentation algorithms for connectomics. Frontiers in neuroanatomy, 2015.
  169. 3d segmentation of neurites in em images challenge-isbi, 2013.
  170. Cracktree: Automatic crack detection from pavement images. Pattern Recognition Letters (PRL), 2012.
  171. Volodymyr Mnih. Machine learning for aerial image labeling. University of Toronto (Canada), 2013.
  172. Ridge-based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging (TMI), 2004.
  173. Rich feature hierarchies for accurate object detection and semantic segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2014.
  174. Computational Topology for Data Analysis. Cambridge University Press, 2021.
  175. Fast is better than free: Revisiting adversarial training. In International Conference on Learning Representations (ICLR), 2019.
  176. Detecting trojaned dnns using counterfactual attributions. arXiv preprint arXiv:2012.02275, 2020.
  177. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  178. Automatic finding of main roads in aerial images by using geometric-stochastic models and estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 1996.
  179. Improved road connectivity by joint learning of orientation and segmentation. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2019.
  180. Spacenet: A remote sensing dataset and challenge series. arXiv preprint arXiv:1807.01232, 2018.
  181. A higher-order crf model for road network extraction. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2013.
  182. Inferring road maps from global positioning system traces: Survey and comparative evaluation. Transportation research record, 2012.
  183. Empirical evaluation of automatically extracted road axes. Empirical evaluation techniques in computer vision, 1998.
  184. Deeproadmapper: Extracting road topology from aerial images. In International Conference on Computer Vision (ICCV), 2017.
  185. Topoal: An adversarial learning approach for topology-aware road segmentation. In European Conference on Computer Vision (ECCV), 2020.
  186. Joint segmentation and path classification of curvilinear structures. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.
  187. Road detection and centerline extraction via deep recurrent convolutional neural network u-net. IEEE Transactions on Geoscience and Remote Sensing, 2019.
  188. A topological-attention convlstm network and its application to em images. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021.
  189. Boundary learning by optimization with topological constraints. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2010.
  190. Allen Hatcher. Algebraic Topology. Cambridge University Press, 2002.
  191. Digital topology: Introduction and survey. Computer Vision, Graphics, and Image Processing, 1989.
  192. A new characterization of three-dimensional simple points. Pattern Recognition Letters (PRL), 1994.
  193. Topology-preserving deformations of two-valued digital pictures. Graphical Models and Image Processing, 1998.
  194. Roadtracer: Automatic extraction of road networks from aerial images. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2018.
  195. Deepglobe 2018: A challenge to parse the earth through satellite images. In CVPR Workshops, 2018.
  196. 3d u-net: learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016.
  197. Vecroad: Point-based iterative graph exploration for road graphs extraction. In IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2020.
  198. icurb: Imitation learning-based detection of road curbs using aerial images for autonomous driving. IEEE Robotics and Automation Letters (RAL), 2021.
  199. R. Forman. Morse theory for cell complexes. Advances in mathematics, 1998.
  200. Thierry Sousbie. The persistent cosmic web and its filamentary structure–i. theory and implementation. Monthly Notices of the Royal Astronomical Society, 2011.
  201. Graph reconstruction by discrete morse theory. In Symposium on Computational Geometry (SoCG), 2018.
  202. Optimal topological simplification of discrete functions on surfaces. Discr. Comput. Geom., 2012.
  203. 3d image reconstruction for comparison of algorithm database: a patient-specific anatomical and medical image database. IRCAD, Strasbourg, France, Tech. Rep, 2010.
  204. Deepem3d: approaching human-level performance on 3d anisotropic em image segmentation. Bioinformatics, 2017.
  205. A survey on active learning and human-in-the-loop deep learning for medical image analysis. Medical Image Analysis (MedIA), 2021.
  206. Troubleshooting image segmentation models with human-in-the-loop. Machine Learning, 2022.
  207. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  208. The lung image database consortium (lidc) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans. Medical physics, 2011.
  209. The cancer imaging archive (tcia): maintaining and operating a public information repository. Journal of digital imaging, 2013.
  210. Learning cellular morphology with neural networks. Nature communications, 2019.
  211. Depression-like episodes in mice harboring mtdna deletions in paraventricular thalamus. Molecular psychiatry, 2016.
  212. Mitochondrial disorders. Brain, 2004.
  213. Exploring the third dimension: volume electron microscopy comes of age. Micron, 2014.
  214. Volume scanning electron microscopy for imaging biological ultrastructure. Biology of the Cell, 2016.
  215. Whole-cell organelle segmentation in volume electron microscopy. Nature, 2021.
  216. Automatic segmentation of mitochondria and endolysosomes in volumetric electron microscopy data. Computers in biology and medicine, 2020.
  217. Segem: efficient image analysis for high-resolution connectomics. Neuron, 2015.
  218. Mitoem dataset: Large-scale 3d mitochondria instance segmentation from em images. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2020.
  219. Trigger hunting with a topological prior for trojan detection. In International Conference on Learning Representations (ICLR), 2022.
  220. Xiaoling Hu. Structure-aware image segmentation with homotopy warping. In Advances in neural information processing systems (NeurIPS), 2022.
  221. Deep statistic shape model for myocardium segmentation. arXiv preprint arXiv:2207.10607, 2022.
  222. 3d topology-preserving segmentation with compound multi-slice representation. In International Symposium on Biomedical Imaging (ISBI), 2021.
  223. Learning topological interactions for multi-class medical image segmentation. In European Conference on Computer Vision (ECCV), 2022.
  224. Topology-aware uncertainty for image segmentation. arXiv preprint arXiv:2306.05671, 2023.
  225. Confidence estimation using unlabeled data. In International Conference on Learning Representations (ICLR), 2023.
  226. Calibrating uncertainty for semi-supervised crowd counting. In International Conference on Computer Vision (ICCV), 2023.
  227. Enhancing modality-agnostic representations via meta-learning for brain tumor segmentation. In International Conference on Computer Vision (ICCV), 2023.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets