Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 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

UnSegGNet: Unsupervised Image Segmentation using Graph Neural Networks (2405.06057v1)

Published 9 May 2024 in cs.CV and cs.LG

Abstract: Image segmentation, the process of partitioning an image into meaningful regions, plays a pivotal role in computer vision and medical imaging applications. Unsupervised segmentation, particularly in the absence of labeled data, remains a challenging task due to the inter-class similarity and variations in intensity and resolution. In this study, we extract high-level features of the input image using pretrained vision transformer. Subsequently, the proposed method leverages the underlying graph structures of the images, seeking to discover and delineate meaningful boundaries using graph neural networks and modularity based optimization criteria without relying on pre-labeled training data. Experimental results on benchmark datasets demonstrate the effectiveness and versatility of the proposed approach, showcasing competitive performance compared to the state-of-the-art unsupervised segmentation methods. This research contributes to the broader field of unsupervised medical imaging and computer vision by presenting an innovative methodology for image segmentation that aligns with real-world challenges. The proposed method holds promise for diverse applications, including medical imaging, remote sensing, and object recognition, where labeled data may be scarce or unavailable. The github repository of the code is available on [https://github.com/ksgr5566/unseggnet]

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. Support vector machines. Springer Science & Business Media, 2008.
  2. Leo Breiman. Random forests. Machine learning, 45:5–32, 2001.
  3. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 2012.
  4. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pages 234–241. Springer, 2015.
  5. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence, 39(12):2481–2495, 2017.
  6. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4):834–848, 2017.
  7. Medical image segmentation using deep learning: A survey. IET Image Processing, 16(5):1243–1267, 2022.
  8. Segment anything in medical images. Nature Communications, 15(1):654, 2024.
  9. Segment anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4015–4026, 2023.
  10. Emerging properties in self-supervised vision transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9650–9660, 2021.
  11. Probabilistic modeling of inter-and intra-observer variability in medical image segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 21097–21106, 2023.
  12. Inter-observer variation in the histopathological diagnosis of clinically suspicious pigmented skin lesions. The Journal of Pathology: A Journal of the Pathological Society of Great Britain and Ireland, 196(4):459–466, 2002.
  13. Watershed segmentation for breast tumor in 2-D sonography. Ultrasound in medicine & biology, 30(5):625–632, 2004.
  14. Unsupervised Medical Image Segmentation Based on the Local Center of Mass. Scientific reports, 8(1):13012, 2018.
  15. The Watershed Transform: Definitions, Algorithms and Parallelization Strategies. Fundamenta informaticae, 41(1-2):187–228, 2000.
  16. Seeded region growing. IEEE Transactions on pattern analysis and machine intelligence, 16(6):641–647, 1994.
  17. Seeded region growing: an extensive and comparative study. Pattern recognition letters, 26(8):1139–1156, 2005.
  18. An efficient local chan–vese model for image segmentation. Pattern Recognition, 43(3):603–618, 2010.
  19. Snakes: Active contour models. International journal of computer vision, 1(4):321–331, 1988.
  20. Data clustering: a review. ACM computing surveys (CSUR), 31(3):264–323, 1999.
  21. Yizong Cheng. Mean shift, mode seeking, and clustering. IEEE transactions on pattern analysis and machine intelligence, 17(8):790–799, 1995.
  22. Slic superpixels compared to state-of-the-art superpixel methods. IEEE transactions on pattern analysis and machine intelligence, 34(11):2274–2282, 2012.
  23. Quick Shift and Kernel Methods for Mode Seeking. In Computer Vision–ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part IV 10, pages 705–718. Springer, 2008.
  24. Unsupervised images segmentation via incremental dictionary learning based sparse representation. Information Sciences, 269:48–59, 2014.
  25. Normalized cuts and image segmentation. IEEE Transactions on pattern analysis and machine intelligence, 22(8):888–905, 2000.
  26. Deep spectral methods: A surprisingly strong baseline for unsupervised semantic segmentation and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8364–8375, 2022.
  27. Spectral clustering with graph neural networks for graph pooling. In International conference on machine learning, pages 874–883. PMLR, 2020.
  28. A goal-driven unsupervised image segmentation method combining graph-based processing and markov random fields. Pattern Recognition, 134:109082, 2023.
  29. Eigenvalue and generalized eigenvalue problems: Tutorial. arXiv preprint arXiv:1903.11240, 2019.
  30. Autoencoders for unsupervised anomaly segmentation in brain mr images: a comparative study. Medical Image Analysis, 69:101952, 2021.
  31. Unsupervised x-ray image segmentation with task driven generative adversarial networks. Medical image analysis, 62:101664, 2020.
  32. Teuvo Kohonen. Essentials of the self-organizing map. Neural networks, 37:52–65, 2013.
  33. Graph clustering with graph neural networks. Journal of Machine Learning Research, 24(127):1–21, 2023.
  34. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  35. Piet Van Mieghem. Graph spectra for complex networks. Cambridge University Press, 2023.
  36. Mark EJ Newman. Modularity and community structure in networks. Proceedings of the national academy of sciences, 103(23):8577–8582, 2006.
  37. Tokencut: Segmenting objects in images and videos with self-supervised transformer and normalized cut. IEEE transactions on pattern analysis and machine intelligence, 2023.
  38. Improving graph neural networks with simple architecture design. arXiv preprint arXiv:2105.07634, 2021.
  39. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  40. Searching for activation functions. arXiv preprint arXiv:1710.05941, 2017.
  41. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks, 107:3–11, 2018.
  42. Big transfer (bit): General visual representation learning. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16, pages 491–507. Springer, 2020.
  43. The graph neural network model. IEEE transactions on neural networks, 20(1):61–80, 2008.
  44. Stand-alone self-attention in vision models. Advances in neural information processing systems, 32, 2019.
  45. Exploring self-attention for image recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10076–10085, 2020.
  46. Vision transformers are robust learners. In Proceedings of the AAAI conference on Artificial Intelligence, volume 36, pages 2071–2081, 2022.
  47. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  48. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics, pages 249–256. JMLR Workshop and Conference Proceedings, 2010.
  49. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  50. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415, 2016.
  51. Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics, pages 315–323. JMLR Workshop and Conference Proceedings, 2011.
  52. Wm-dova maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized medical imaging and graphics, 43:99–111, 2015.
  53. Kvasir-seg: A segmented polyp dataset. In MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5–8, 2020, Proceedings, Part II 26, pages 451–462. Springer, 2020.
  54. Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368, 2019.
  55. Hierarchical image saliency detection on extended cssd. IEEE transactions on pattern analysis and machine intelligence, 38(4):717–729, 2015.
  56. Learning to detect salient objects with image-level supervision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 136–145, 2017.
  57. The caltech-ucsd birds-200-2011 dataset. 2011.
  58. Deepcut: Unsupervised segmentation using graph neural networks clustering. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 32–41, 2023.
  59. An efficient k-means clustering algorithm: Analysis and implementation. IEEE transactions on pattern analysis and machine intelligence, 24(7):881–892, 2002.
Citations (1)
View on Semantic Scholar

Summary

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

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