Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Contour-based Interactive Segmentation (2302.06353v2)

Published 13 Feb 2023 in cs.CV

Abstract: Recent advances in interactive segmentation (IS) allow speeding up and simplifying image editing and labeling greatly. The majority of modern IS approaches accept user input in the form of clicks. However, using clicks may require too many user interactions, especially when selecting small objects, minor parts of an object, or a group of objects of the same type. In this paper, we consider such a natural form of user interaction as a loose contour, and introduce a contour-based IS method. We evaluate the proposed method on the standard segmentation benchmarks, our novel UserContours dataset, and its subset UserContours-G containing difficult segmentation cases. Through experiments, we demonstrate that a single contour provides the same accuracy as multiple clicks, thus reducing the required amount of user interactions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Efficient interactive annotation of segmentation datasets with polygon-RNN+⁣++++ +. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 859–868. IEEE, jun 2018.
  2. Interactive full image segmentation by considering all regions jointly. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11622–11631. IEEE, jun 2019.
  3. Interactive full image segmentation by considering all regions jointly. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  4. Efficient full image interactive segmentation by leveraging within-image appearance similarity. arXiv preprint arXiv:2007.08173, 2020.
  5. Error-tolerant scribbles based interactive image segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
  6. icoseg: Interactive co-segmentation with intelligent scribble guidance. 2010.
  7. Large-scale interactive object segmentation with human annotators. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11700–11709, 2019.
  8. Interactive graph cuts for optimal boundary & region segmentation of objects in n-d images. In IEEE/CVF International Conference on Computer Vision (ICCV), volume 1, pages 105–112. IEEE Comput. Soc, 2001.
  9. DenseCut: Densely connected CRFs for realtime GrabCut. Computer Graphics Forum, 34(7):193–201, oct 2015.
  10. ImageNet: A large-scale hierarchical image database. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 248–255. IEEE, jun 2009.
  11. PhraseClick: Toward achieving flexible interactive segmentation by phrase and click. In IEEE/CVF European Conference on Computer Vision (ECCV), pages 417–435. Springer International Publishing, 2020.
  12. D. Freedman and Tao Zhang. Interactive graph cut based segmentation with shape priors. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 755–762. IEEE, 2005.
  13. L. Grady. Random walks for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(11):1768–1783, nov 2006.
  14. Latency management in scribble-based interactive segmentation of medical images. IEEE Transactions on Biomedical Engineering, 2017.
  15. Geodesic star convexity for interactive image segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3129–3136. IEEE, jun 2010.
  16. Lvis: A dataset for large vocabulary instance segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5356–5364, 2019.
  17. Edgeflow: Achieving practical interactive segmentation with edge-guided flow. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1551–1560, 2021.
  18. Semantic contours from inverse detectors. In IEEE/CVF International Conference on Computer Vision (ICCV), pages 991–998. IEEE, 2011.
  19. Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407, 2018.
  20. Interactive image segmentation via backpropagating refinement scheme. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5297–5306, 2019.
  21. Generative image segmentation using random walks with restart. In IEEE/CVF European Conference on Computer Vision (ECCV), pages 264–275. Springer Berlin Heidelberg, 2008.
  22. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  23. Continuous adaptation for interactive object segmentation by learning from corrections. In IEEE/CVF European Conference on Computer Vision (ECCV), pages 579–596. Springer International Publishing, 2020.
  24. The open images dataset v4. International Journal of Computer Vision, 128(7):1956–1981, 2020.
  25. Interactive image segmentation with latent diversity. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  26. Regional interactive image segmentation networks. In IEEE/CVF International Conference on Computer Vision (ICCV), pages 2746–2754. IEEE, oct 2017.
  27. MultiSeg: Semantically meaningful, scale-diverse segmentations from minimal user input. In IEEE/CVF International Conference on Computer Vision (ICCV), pages 662–670. IEEE, oct 2019.
  28. Deep interactive thin object selection. In WACV, 2021.
  29. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014.
  30. ScribbleSup: Scribble-supervised convolutional networks for semantic segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3159–3167. IEEE, jun 2016.
  31. Interactive image segmentation with first click attention. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 13339–13348. IEEE, jun 2020.
  32. Deep extreme cut: From extreme points to object segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 616–625. IEEE, jun 2018.
  33. Deep extreme cut: From extreme points to object segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  34. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In IEEE/CVF International Conference on Computer Vision (ICCV), volume 2, pages 416–423. IEEE, 2001.
  35. A comparative evaluation of interactive segmentation algorithms. Pattern Recognition, 43(2):434–444, 2010.
  36. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
  37. A benchmark dataset and evaluation methodology for video object segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 724–732, 2016.
  38. ”grabcut” interactive foreground extraction using iterated graph cuts. ACM transactions on graphics (TOG), 23(3):309–314, 2004.
  39. f-brs: Rethinking backpropagating refinement for interactive segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8623–8632, 2020.
  40. Reviving iterative training with mask guidance for interactive segmentation. arXiv preprint arXiv:2102.06583, 2021.
  41. Deep high-resolution representation learning for visual recognition. TPAMI, 2019.
  42. MILCut: A sweeping line multiple instance learning paradigm for interactive image segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 256–263. IEEE, jun 2014.
  43. Deep interactive object selection. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 373–381, 2016.
  44. Deep grabcut for object selection. arXiv preprint arXiv:1707.00243, 2017.
  45. Object-contextual representations for semantic segmentation. 2020.
  46. Interactive object segmentation with inside-outside guidance. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 12234–12244. IEEE, jun 2020.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Danil Galeev (4 papers)
  2. Polina Popenova (2 papers)
  3. Anna Vorontsova (19 papers)
  4. Anton Konushin (33 papers)
Citations (5)
View on Semantic Scholar

Summary

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

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