Bayesian Semantic Instance Segmentation in Open Set World

  • Trung PhamEmail author
  • B. G. Vijay Kumar
  • Thanh-Toan Do
  • Gustavo Carneiro
  • Ian Reid
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11214)


This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires annotation masks for all object instances, which is expensive to acquire or even infeasible in some realistic scenarios, where the number of categories may increase boundlessly. In this paper, we present a novel open-set semantic instance segmentation approach capable of segmenting all known and unknown object classes in images, based on the output of an object detector trained on known object classes. We formulate the problem using a Bayesian framework, where the posterior distribution is approximated with a simulated annealing optimization equipped with an efficient image partition sampler. We show empirically that our method is competitive with state-of-the-art supervised methods on known classes, but also performs well on unknown classes when compared with unsupervised methods.


Instance segmentation Open-set conditions 



This research was supported by the Australian Research Council through the Centre of Excellence for Robotic Vision (CE140100016) and by Discover Project (DP180103232).


  1. 1.
    Arbelaez, P.: Boundary extraction in natural images using ultrametric contour maps. In: 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW 2006), pp. 182–182, June 2006.
  2. 2.
    Bai, M., Urtasun, R.: Deep watershed transform for instance segmentation. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 2858–2866 (2017)Google Scholar
  3. 3.
    Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223 (2016)Google Scholar
  4. 4.
    Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: CVPR (2016)Google Scholar
  5. 5.
    Fathi, A., et al.: Semantic instance segmentation via deep metric learning. CoRR abs/1703.10277 (2017)Google Scholar
  6. 6.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)CrossRefGoogle Scholar
  7. 7.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. arXiv preprint arXiv:1703.06870 (2017)
  8. 8.
    Hu, R., Dollár, P., He, K., Darrell, T., Girshick, R.B.: Learning to segment every thing. CoRR abs/1711.10370 (2017).
  9. 9.
    Kim, C.J., Nelson, C.R., et al.: State-Space Models with Regime Switching: Classical and Gibbs-Sampling Approaches with Applications, vol. 1. MIT Press, Cambridge (1999)Google Scholar
  10. 10.
    Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: CVPR, July 2017Google Scholar
  11. 11.
    Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). Scholar
  12. 12.
    Maninis, K., Pont-Tuset, J., Arbeláez, P., Gool, L.V.: Convolutional oriented boundaries: from image segmentation to high-level tasks. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 40(4), 819–833 (2017)CrossRefGoogle Scholar
  13. 13.
    Milan, A., et al.: Semantic segmentation from limited training data. CoRR abs/1709.07665 (2017)Google Scholar
  14. 14.
    Pham, T., Do, T.T., Sünderhauf, N., Reid, I.: SceneCut: joint geometric and object segmentation for indoor scenes. In: 2018 IEEE International Conference on Robotics and Automation (ICRA) (2018)Google Scholar
  15. 15.
    Pham, T.T., Eich, M., Reid, I.D., Wyeth, G.: Geometrically consistent plane extraction for dense indoor 3D maps segmentation. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4199–4204 (2016)Google Scholar
  16. 16.
    Pham, T.T., Reid, I.D., Latif, Y., Gould, S.: Hierarchical higher-order regression forest fields: an application to 3D indoor scene labelling. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2246–2254 (2015)Google Scholar
  17. 17.
    Pinheiro, P.O., Collobert, R., Dollár, P.: Learning to segment object candidates. In: NIPS (2015)Google Scholar
  18. 18.
    Pinheiro, P.O., Lin, T.-Y., Collobert, R., Dollár, P.: Learning to refine object segments. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 75–91. Springer, Cham (2016). Scholar
  19. 19.
    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. CoRR abs/1612.08242 (2016)Google Scholar
  20. 20.
    Ren, M., Zemel, R.S.: End-to-end instance segmentation with recurrent attention. In: CVPR (2017)Google Scholar
  21. 21.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)Google Scholar
  22. 22.
    Romera-Paredes, B., Torr, P.H.S.: Recurrent instance segmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 312–329. Springer, Cham (2016). Scholar
  23. 23.
    Scheirer, W.J., de Rezende Rocha, A., Sapkota, A., Boult, T.E.: Toward open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1757–1772 (2013)CrossRefGoogle Scholar
  24. 24.
    Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746–760. Springer, Heidelberg (2012). Scholar
  25. 25.
    Sünderhauf, N., Pham, T.T., Latif, Y., Milford, M., Reid, I.D.: Meaningful maps with object-oriented semantic mapping. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (2017)Google Scholar
  26. 26.
    Trevor, A.J.B., Gedikli, S., Rusu, R.B., Christensen, H.I.: Efficient organized point cloud segmentation with connected components (2013)Google Scholar
  27. 27.
    Tu, Z., Zhu, S.C.: Image segmentation by data-driven Markov chain monte carlo. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 657–673 (2002)CrossRefGoogle Scholar
  28. 28.
    Van Laarhoven, P.J., Aarts, E.H.: Simulated annealing. In: Van Laarhoven, P.J., Aarts, E.H. (eds.) Simulated Annealing: Theory and Applications, pp. 7–15. Springer, Dordrecht (1987). Scholar
  29. 29.
    Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Trung Pham
    • 1
    Email author
  • B. G. Vijay Kumar
    • 1
  • Thanh-Toan Do
    • 1
  • Gustavo Carneiro
    • 1
  • Ian Reid
    • 1
  1. 1.School of Computer ScienceThe University of AdelaideAdelaideAustralia

Personalised recommendations