Advertisement

Semi-supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation

  • Huiling WangEmail author
  • Tapani Raiko
  • Lasse Lensu
  • Tinghuai Wang
  • Juha Karhunen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10111)

Abstract

Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labelled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively exploiting the representation power of CNN with limited training data remains a challenge. Simply borrowing the existing pre-trained CNN image recognition model for video segmentation task can severely hurt performance. We propose a semi-supervised approach to adapting CNN image recognition model trained from labelled image data to the target domain exploiting both semantic evidence learned from CNN, and the intrinsic structures of video data. By explicitly modelling and compensating for the domain shift from the source domain to the target domain, this proposed approach underpins a robust semantic object segmentation method against the changes in appearance, shape and occlusion in natural videos. We present extensive experiments on challenging datasets that demonstrate the superior performance of our approach compared with the state-of-the-art methods.

Keywords

Optical Flow Target Domain Domain Adaptation Convolutional Neural Network Object Segmentation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 282–295. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15555-0_21 CrossRefGoogle Scholar
  2. 2.
    Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: ICCV, pp. 1995–2002 (2011)Google Scholar
  3. 3.
    Zhang, D., Javed, O., Shah, M.: Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In: CVPR, pp. 628–635 (2013)Google Scholar
  4. 4.
    Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: ICCV, pp. 1777–1784 (2013)Google Scholar
  5. 5.
    Wang, T., Wang, H.: Graph transduction learning of object proposals for video object segmentation. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 553–568. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-16817-3_36 Google Scholar
  6. 6.
    Wang, H., Wang, T.: Primary object discovery and segmentation in videos via graph-based transductive inference. Comput. Vis. Image Underst. 143, 159–172 (2016)CrossRefGoogle Scholar
  7. 7.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)Google Scholar
  8. 8.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition, arXiv preprint (2014). arXiv:1409.1556
  9. 9.
    Rasmus, A., Valpola, H., Honkala, M., Berglund, M., Raiko, T.: Semi-supervised learning with ladder network. In: NIPS (2015)Google Scholar
  10. 10.
    Faktor, A., Irani, M.: Video segmentation by non-local consensus voting. In: BMVC, vol. 2, p. 6 (2014)Google Scholar
  11. 11.
    Yang, J., Zhao, G., Yuan, J., Shen, X., Lin, Z., Price, B., Brandt, J.: Discovering primary objects in videos by saliency fusion and iterative appearance estimation. IEEE Trans. Circuits Syst, Video Technol (2015)Google Scholar
  12. 12.
    Perazzi, F., Wang, O., Gross, M., Sorkine-Hornung, A.: Fully connected object proposals for video segmentation. In: ICCV, pp. 3227–3234 (2015)Google Scholar
  13. 13.
    Endres, I., Hoiem, D.: Category independent object proposals. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 575–588. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15555-0_42 CrossRefGoogle Scholar
  14. 14.
    Manen, S., Guillaumin, M., Gool, L.J.V.: Prime object proposals with randomized prim’s algorithm. In: ICCV, pp. 2536–2543 (2013)Google Scholar
  15. 15.
    Wang, J., Xu, Y., Shum, H.Y., Cohen, M.F.: Video tooning. ACM Trans. Graph. 23, 574–583 (2004)CrossRefGoogle Scholar
  16. 16.
    Collomosse, J.P., Rowntree, D., Hall, P.M.: Stroke surfaces: temporally coherent artistic animations from video. IEEE Trans. Vis. Comput. Graph. 11, 540–549 (2005)CrossRefGoogle Scholar
  17. 17.
    Wang, T., Collomosse, J.P.: Probabilistic motion diffusion of labeling priors for coherent video segmentation. IEEE Trans. Multimed. 14, 389–400 (2012)CrossRefGoogle Scholar
  18. 18.
    Tsai, D., Flagg, M., Nakazawa, A., Rehg, J.M.: Motion coherent tracking using multi-label MRF optimization. Int. J. Comput. Vis. 100, 190–202 (2012)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Li, F., Kim, T., Humayun, A., Tsai, D., Rehg, J.M.: Video segmentation by tracking many figure-ground segments. In: ICCV, Australia, 1–8 December 2013, pp. 2192–2199 (2013)Google Scholar
  20. 20.
    Wang, T., Han, B., Collomosse, J.P.: Touchcut: fast image and video segmentation using single-touch interaction. Comput. Vis. Image Underst. 120, 14–30 (2014)CrossRefGoogle Scholar
  21. 21.
    Grundmann, M., Kwatra, V., Han, M., Essa, I.A.: Efficient hierarchical graph-based video segmentation. In: CVPR, pp. 2141–2148 (2010)Google Scholar
  22. 22.
    Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 626–639. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33783-3_45 CrossRefGoogle Scholar
  23. 23.
    Wang, C., de La Gorce, M., Paragios, N.: Segmentation, ordering and multi-object tracking using graphical models. In: ICCV, pp. 747–754 (2009)Google Scholar
  24. 24.
    Sundberg, P., Brox, T., Maire, M., Arbelaez, P., Malik, J.: Occlusion boundary detection and figure/ground assignment from optical flow. In: CVPR, pp. 2233–2240 (2011)Google Scholar
  25. 25.
    Giordano, D., Murabito, F., Palazzo, S., Spampinato, C.: Superpixel-based video object segmentation using perceptual organization and location prior. In: CVPR, pp. 4814–4822 (2015)Google Scholar
  26. 26.
    Taylor, B., Karasev, V., Soatto, S.: Causal video object segmentation from persistence of occlusions. In: CVPR, pp. 4268–4276 (2015)Google Scholar
  27. 27.
    Wang, W., Shen, J., Porikli, F.: Saliency-aware geodesic video object segmentation. In: CVPR, pp. 3395–3402 (2015)Google Scholar
  28. 28.
    Hartmann, G., Grundmann, M., Hoffman, J., Tsai, D., Kwatra, V., Madani, O., Vijayanarasimhan, S., Essa, I., Rehg, J., Sukthankar, R.: Weakly supervised learning of object segmentations from web-scale video. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7583, pp. 198–208. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33863-2_20 CrossRefGoogle Scholar
  29. 29.
    Tang, K.D., Sukthankar, R., Yagnik, J., Li, F.: Discriminative segment annotation in weakly labeled video. In: CVPR, pp. 2483–2490 (2013)Google Scholar
  30. 30.
    Liu, X., Tao, D., Song, M., Ruan, Y., Chen, C., Bu, J.: Weakly supervised multiclass video segmentation. In: CVPR, pp. 57–64 (2014)Google Scholar
  31. 31.
    Zhang, Y., Chen, X., Li, J., Wang, C., Xia, C.: Semantic object segmentation via detection in weakly labeled video. In: CVPR, pp. 3641–3649 (2015)Google Scholar
  32. 32.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580–587 (2014)Google Scholar
  33. 33.
    Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Sch, B.: Learning with local and global consistency. In: NIPS, pp. 321–328 (2004)Google Scholar
  34. 34.
    Rother, C., Kolmogorov, V., Blake, A.: “GrabCut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23, 309–314 (2004)CrossRefGoogle Scholar
  35. 35.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1222–1239 (2001)CrossRefGoogle Scholar
  36. 36.
    Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference on Multimedia, pp. 675–678. ACM (2014)Google Scholar
  37. 37.
    Arbelaez, P., Maire, M., Fowlkes, C.C., Malik, J.: From contours to regions: an empirical evaluation. In: CVPR, pp. 2294–2301 (2009)Google Scholar
  38. 38.
    Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004). doi: 10.1007/978-3-540-24673-2_3 CrossRefGoogle Scholar
  39. 39.
    Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 282–295. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15555-0_21 CrossRefGoogle Scholar
  40. 40.
    Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: CVPR, pp. 3282–3289 (2012)Google Scholar
  41. 41.
    Jain, S.D., Grauman, K.: Supervoxel-consistent foreground propagation in video. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 656–671. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10593-2_43 Google Scholar
  42. 42.
    Wang, L., Hua, G., Sukthankar, R., Xue, J., Zheng, N.: Video object discovery and co-segmentation with extremely weak supervision. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 640–655. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10593-2_42 Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Huiling Wang
    • 1
    Email author
  • Tapani Raiko
    • 1
  • Lasse Lensu
    • 2
  • Tinghuai Wang
    • 3
  • Juha Karhunen
    • 1
  1. 1.Aalto UniversityEspooFinland
  2. 2.Lappeenranta University of TechnologyLappeenrantaFinland
  3. 3.Nokia TechnologiesTampereFinland

Personalised recommendations