Papers
Topics
Authors
Recent
Search
2000 character limit reached

A Graph Multi-separator Problem for Image Segmentation

Published 10 Jul 2023 in cs.CV and cs.DM | (2307.04592v1)

Abstract: We propose a novel abstraction of the image segmentation task in the form of a combinatorial optimization problem that we call the multi-separator problem. Feasible solutions indicate for every pixel whether it belongs to a segment or a segment separator, and indicate for pairs of pixels whether or not the pixels belong to the same segment. This is in contrast to the closely related lifted multicut problem where every pixel is associated to a segment and no pixel explicitly represents a separating structure. While the multi-separator problem is NP-hard, we identify two special cases for which it can be solved efficiently. Moreover, we define two local search algorithms for the general case and demonstrate their effectiveness in segmenting simulated volume images of foam cells and filaments.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Hierarchical image segmentation using correlation clustering. IEEE Trans. Neural Networks Learn. Syst., 27(6):1358–1367, 2016. doi: 10.1109/TNNLS.2015.2505181.
  2. Probabilistic image segmentation with closedness constraints. In ICCV, 2011. doi: 10.1109/ICCV.2011.6126550.
  3. A polyhedral study of lifted multicuts. Discrete Optimization, 47:100757, 2023. doi: 10.1016/j.disopt.2022.100757.
  4. Multidimensional scaling of measures of distance between partitions. Journal of Mathematical Psychology, 10(2):148–203, 1973. doi: 10.1016/0022-2496(73)90012-6.
  5. Optimal coalition structure generation in cooperative graph games. In AAAI, 2013. doi: 10.1609/aaai.v27i1.8653.
  6. Egon Balas and Cid Carvalho de Souza. The vertex separator problem: a polyhedral investigation. Mathematical Programming, 103(3):583–608, 2005. doi: 10.1007/s10107-005-0574-7.
  7. Correlation clustering. Machine learning, 56:89–113, 2004. doi: 10.1023/B:MACH.0000033116.57574.95.
  8. Francisco Barahona. On the computational complexity of Ising spin glass models. Journal of Physics A: Mathematical and General, 15(10):3241, 1982. doi: 10.1088/0305-4470/15/10/028.
  9. Cut, glue & cut: A fast, approximate solver for multicut partitioning. In CVPR, 2014. doi: 10.1109/CVPR.2014.17.
  10. Fusion moves for correlation clustering. In CVPR, 2015. doi: 10.1109/CVPR.2015.7298973.
  11. Multicut brings automated neurite segmentation closer to human performance. Nature methods, 14(2):101–102, 2017. doi: 10.1038/nmeth.4151.
  12. Generating all the minimal separators of a graph. International Journal of Foundations of Computer Science, 11(03):397–403, 2000. doi: 10.1142/S0129054100000211.
  13. Clustering with qualitative information. Journal of Computer and System Sciences, 71(3):360–383, 2005. doi: 10.1016/j.jcss.2004.10.012.
  14. The partition problem. Mathematical programming, 59(1-3):87–115, 1993. doi: 10.1007/BF01581239.
  15. The vertex k-cut problem. Discrete Optimization, 31:8–28, 2018. doi: 10.1016/j.disopt.2018.07.003.
  16. The multi-terminal vertex separator problem: Polyhedral analysis and branch-and-cut. Discrete Applied Mathematics, 256:11–37, 2019. doi: 10.1016/j.dam.2018.10.005.
  17. Correlation clustering in general weighted graphs. Theoretical Computer Science, 361(2-3):172–187, 2006. doi: 10.1016/j.tcs.2006.05.008.
  18. An exact algorithm for solving the vertex separator problem. Journal of Global Optimization, 49:425–434, 2011.
  19. Fernando Escalante. Schnittverbände in Graphen. Abh.Math.Semin.Univ.Hambg., 38:199–220, 1972. doi: 10.1007/BF02996932.
  20. Junichiro Fukuyama. NP-completeness of the planar separator problems. J. Graph Algorithms Appl., 10(2):317–328, 2006. doi: 10.7155/jgaa.00130.
  21. On integer and bilevel formulations for the k-vertex cut problem. Mathematical Programming Computation, 12:133–164, 2020. doi: 10.1007/s12532-019-00167-1.
  22. Multiway cuts in directed and node weighted graphs. In ICALP, 1994. doi: 10.1007/3-540-58201-0˙92.
  23. Multiway cuts in node weighted graphs. Journal of Algorithms, 50(1):49–61, 2004. doi: 10.1016/S0196-6774(03)00111-1.
  24. The ellipsoid method and its consequences in combinatorial optimization. Combinatorica, 1(2):169–197, 1981. doi: 10.1007/BF02579273.
  25. Poly-logarithmic deterministic fully-dynamic algorithms for connectivity, minimum spanning tree, 2-edge, and biconnectivity. Journal of the ACM (JACM), 48(4):723–760, 2001. doi: 10.1145/502090.502095.
  26. Algorithm 447: efficient algorithms for graph manipulation. Communications of the ACM, 16(6):372–378, 1973. doi: 10.1145/362248.362272.
  27. Analysis and optimization of graph decompositions by lifted multicuts. In ICML, 2017. URL https://proceedings.mlr.press/v70/hornakova17a.html.
  28. Lifted disjoint paths with application in multiple object tracking. In ICML, 2020. URL http://proceedings.mlr.press/v119/hornakova20a.html.
  29. Globally optimal image partitioning by multicuts. In EMMCVPR, 2011. doi: 10.1007/978-3-642-23094-3˙3.
  30. Higher-order segmentation via multicuts. Computer Vision and Image Understanding, 143:104–119, 2016a. doi: 10.1016/j.cviu.2015.11.005.
  31. Multicuts and perturb & MAP for probabilistic graph clustering. J. Math. Imaging Vis., 56(2):221–237, 2016b. doi: 10.1007/s10851-016-0659-3.
  32. Solving minimum cost lifted multicut problems by node agglomeration. In ACCV, 2018. doi: 10.1007/978-3-030-20870-7˙5.
  33. Uncertainty in minimum cost multicuts for image and motion segmentation. In UAI, 2021. URL https://proceedings.mlr.press/v161/kardoost21a.html.
  34. Richard Manning Karp. Reducibility among combinatorial problems. In Complexity of computer computations, 1972. doi: 10.1007/978-1-4684-2001-2˙9.
  35. Margret Keuper. Higher-order minimum cost lifted multicuts for motion segmentation. In ICCV, 2017. doi: 10.1109/ICCV.2017.455.
  36. Efficient decomposition of image and mesh graphs by lifted multicuts. In ICCV, 2015. doi: 10.1109/ICCV.2015.204.
  37. Image segmentation using higher-order correlation clustering. IEEE Trans. Pattern Anal. Mach. Intell., 36(9):1761–1774, 2014. doi: 10.1109/TPAMI.2014.2303095.
  38. InstanceCut: from edges to instances with multicut. In CVPR, 2017. doi: 10.1109/CVPR.2017.774.
  39. Correlation clustering and two-edge-connected augmentation for planar graphs. Algorithmica, pages 1–34, 2023. doi: 10.1007/s00453-023-01128-w.
  40. Learning and segmenting dense voxel embeddings for 3d neuron reconstruction. IEEE Transactions on Medical Imaging, 40(12):3801–3811, 2021. doi: 10.1109/TMI.2021.3097826.
  41. A separator theorem for planar graphs. SIAM Journal on Applied Mathematics, 36(2):177–189, 1979. doi: 10.1137/0136016.
  42. The multi-terminal vertex separator problem: Branch-and-cut-and-price. Discrete Applied Mathematics, 290:86–111, 2021. doi: 10.1016/j.dam.2020.06.021.
  43. Marina Meilă. Comparing clusterings—an information based distance. Journal of Multivariate Analysis, 98(5):873–895, 2007. doi: 10.1016/j.jmva.2006.11.013.
  44. Karl Menger. Zur allgemeinen Kurventheorie. Fundamenta Mathematicae, 10(1):96–115, 1927. URL http://eudml.org/doc/211191.
  45. Fernand Meyer. Un algorithme optimal pour la ligne de partage des eaux. In 8e congrès de reconnaissance des formes et intelligence artificielle, 1991.
  46. Image segmentation using deep learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7):3523–3542, 2022. doi: 10.1109/TPAMI.2021.3059968.
  47. Approximation algorithms for constrained node weighted Steiner tree problems. SIAM Journal on Computing, 37(2):460–481, 2007. doi: 10.1137/S0097539702420474.
  48. Global interactions in random field models: A potential function ensuring connectedness. SIAM J. Imaging Sci., 3(4):1048–1074, 2010. doi: 10.1137/090752614.
  49. Reconstructing cerebrovascular networks under local physiological constraints by integer programming. Medical Image Analysis, 25(1):86–94, 2015. doi: 10.1016/j.media.2015.03.008.
  50. The watershed transform: Definitions, algorithms and parallelization strategies. Fundamenta informaticae, 41(1-2):187–228, 2000. doi: 10.3233/FI-2000-411207.
  51. Relationformer: A unified framework for image-to-graph generation. In ECCV, 2022. doi: 10.1007/978-3-031-19836-6˙24.
  52. Cid Carvalho de Souza and Egon Balas. The vertex separator problem: algorithms and computations. Mathematical Programming, 103(3):609–631, 2005. doi: 10.1007/s10107-005-0573-8.
  53. Multiple people tracking by lifted multicut and person re-identification. In CVPR, 2017. doi: 10.1109/CVPR.2017.394.
  54. Reconstructing curvilinear networks using path classifiers and integer programming. IEEE Trans. Pattern Anal. Mach. Intell., 38(12):2515–2530, 2016. doi: 10.1109/TPAMI.2016.2519025.
  55. scikit-image: image processing in Python. PeerJ, 2:e453, 6 2014. doi: 10.7717/peerj.453.
  56. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans. Pattern Anal. Mach. Intell., 13(6):583–598, 1991. doi: 10.1109/34.87344.
  57. Coalition structure generation over graphs. Journal of Artificial Intelligence Research, 45:165–196, 2012. doi: 10.1613/jair.3715.
  58. The mutex watershed and its objective: Efficient, parameter-free graph partitioning. IEEE Trans. Pattern Anal. Mach. Intell., 43(10):3724–3738, 2020. doi: 10.1109/TPAMI.2020.2980827.
  59. Fast planar correlation clustering for image segmentation. In ECCV, 2012. doi: 10.1007/978-3-642-33783-3˙41.
  60. Cell detection and segmentation using correlation clustering. In MICCAI, 2014. doi: 10.1007/978-3-319-10404-1˙2.

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up