Video Object Segmentation with Episodic Graph Memory Networks

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12348)


How to make a segmentation model efficiently adapt to a specific video as well as online target appearance variations is a fundamental issue in the field of video object segmentation. In this work, a graph memory network is developed to address the novel idea of “learning to update the segmentation model”. Specifically, we exploit an episodic memory network, organized as a fully connected graph, to store frames as nodes and capture cross-frame correlations by edges. Further, learnable controllers are embedded to ease memory reading and writing, as well as maintain a fixed memory scale. The structured, external memory design enables our model to comprehensively mine and quickly store new knowledge, even with limited visual information, and the differentiable memory controllers slowly learn an abstract method for storing useful representations in the memory and how to later use these representations for prediction, via gradient descent. In addition, the proposed graph memory network yields a neat yet principled framework, which can generalize well to both one-shot and zero-shot video object segmentation tasks. Extensive experiments on four challenging benchmark datasets verify that our graph memory network is able to facilitate the adaptation of the segmentation network for case-by-case video object segmentation.


Video segmentation Episodic graph memory Learn to update 



This work was partially supported by Zhejiang Lab’s Open Fund (No. 2019KD0AB04), Zhejiang Lab’s International Talent Fund for Young Professionals, CCF-Tencent Open Fund, ETH Zürich Fund (OK), an Huawei Technologies Oy (Finland) project, an Amazon AWS grant, and Nvidia..

Supplementary material

504435_1_En_39_MOESM1_ESM.pdf (1 mb)
Supplementary material 1 (pdf 1042 KB)


  1. 1.
    Badrinarayanan, V., Galasso, F., Cipolla, R.: Label propagation in video sequences. In: CVPR (2010)Google Scholar
  2. 2.
    Ballas, N., Yao, L., Pal, C., Courville, A.: Delving deeper into convolutional networks for learning video representations. In: ICLR (2016)Google Scholar
  3. 3.
    Bao, L., Wu, B., Liu, W.: CNN in MRF: video object segmentation via inference in a CNN-based higher-order spatio-temporal MRF. In: CVPR (2018)Google Scholar
  4. 4.
    Behl, H.S., Najafi, M., Arnab, A., Torr, P.H.: Meta learning deep visual words for fast video object segmentation. In: NeurIPS Workshop (2019)Google Scholar
  5. 5.
    Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taixé, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR (2017)Google Scholar
  6. 6.
    Chen, Y., Pont-Tuset, J., Montes, A., Van Gool, L.: Blazingly fast video object segmentation with pixel-wise metric learning. In: CVPR (2018)Google Scholar
  7. 7.
    Cheng, J., Tsai, Y.H., Hung, W.C., Wang, S., Yang, M.H.: Fast and accurate online video object segmentation via tracking parts. In: CVPR (2018)Google Scholar
  8. 8.
    Cheng, J., Tsai, Y.H., Wang, S., Yang, M.H.: SegFlow: joint learning for video object segmentation and optical flow. In: ICCV (2017)Google Scholar
  9. 9.
    Cheng, M.M., Mitra, N.J., Huang, X., Torr, P.H., Hu, S.M.: Global contrast based salient region detection. IEEE TPAMI 37(3), 569–582 (2015)CrossRefGoogle Scholar
  10. 10.
    Ci, H., Wang, C., Wang, Y.: Video object segmentation by learning location-sensitive embeddings. In: ECCV (2018)Google Scholar
  11. 11.
    Duarte, K., Rawat, Y.S., Shah, M.: CapsuleVOS: semi-supervised video object segmentation using capsule routing. In: ICCV (2019)Google Scholar
  12. 12.
    Faktor, A., Irani, M.: Video segmentation by non-local consensus voting. In: BMVC (2014)Google Scholar
  13. 13.
    Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)Google Scholar
  14. 14.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  15. 15.
    Hu, Y.-T., Huang, J.-B., Schwing, A.G.: VideoMatch: matching based video object segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 56–73. Springer, Cham (2018). Scholar
  16. 16.
    Jain, S.D., Xiong, B., Grauman, K.: FusionSeg: learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In: CVPR (2017)Google Scholar
  17. 17.
    Johnander, J., Danelljan, M., Brissman, E., Khan, F.S., Felsberg, M.: A generative appearance model for end-to-end video object segmentation. In: CVPR (2019)Google Scholar
  18. 18.
    Keuper, M., Andres, B., Brox, T.: Motion trajectory segmentation via minimum cost multicuts. In: ICCV (2015)Google Scholar
  19. 19.
    Koh, Y.J., Kim, C.: Primary object segmentation in videos based on region augmentation and reduction. In: CVPR (2017)Google Scholar
  20. 20.
    Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. In: NIPS (2011)Google Scholar
  21. 21.
    Kumar, A., et al.: Ask me anything: dynamic memory networks for natural language processing. In: ICML (2016)Google Scholar
  22. 22.
    Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: ICCV (2011)Google Scholar
  23. 23.
    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
  24. 24.
    Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., Porikli, F.: See more, know more: unsupervised video object segmentation with co-attention Siamese networks. In: CVPR (2019)Google Scholar
  25. 25.
    Lu, X., Wang, W., Shen, J., Tai, Y.W., Crandall, D.J., Hoi, S.C.: Learning video object segmentation from unlabeled videos. In: CVPR (2020)Google Scholar
  26. 26.
    Luiten, J., Voigtlaender, P., Leibe, B.: PReMVOS: proposal-generation, refinement and merging for video object segmentation. In: ACCV (2018)Google Scholar
  27. 27.
    Maninis, K.K., et al.: Video object segmentation without temporal information. IEEE TPAMI 41(6), 1515–1530 (2018)CrossRefGoogle Scholar
  28. 28.
    Miller, A., Fisch, A., Dodge, J., Karimi, A.H., Bordes, A., Weston, J.: Key-value memory networks for directly reading documents. In: EMNLP (2016)Google Scholar
  29. 29.
    Ochs, P., Brox, T.: Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions. In: ICCV (2011)Google Scholar
  30. 30.
    Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. IEEE TPAMI 36(6), 1187–1200 (2014)CrossRefGoogle Scholar
  31. 31.
    Oh, S.W., Lee, J.Y., Xu, N., Kim, S.J.: Video object segmentation using space-time memory networks. In: ICCV (2019)Google Scholar
  32. 32.
    Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. In: ICCV (2013)Google Scholar
  33. 33.
    Perazzi, F., Khoreva, A., Benenson, R., Schiele, B., Sorkine-Hornung, A.: Learning video object segmentation from static images. In: CVPR (2017)Google Scholar
  34. 34.
    Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: CVPR (2016)Google Scholar
  35. 35.
    Perazzi, F., Wang, O., Gross, M., Sorkine-Hornung, A.: Fully connected object proposals for video segmentation. In: CVPR (2015)Google Scholar
  36. 36.
    Pont-Tuset, J., Perazzi, F., Caelles, S., Arbeláez, P., Sorkine-Hornung, A., Van Gool, L.: The 2017 DAVIS challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)
  37. 37.
    Prest, A., Leistner, C., Civera, J., Schmid, C., Ferrari, V.: Learning object class detectors from weakly annotated video. In: CVPR (2012)Google Scholar
  38. 38.
    Rakelly, K., Shelhamer, E., Darrell, T., Efros, A.A., Levine, S.: Meta-learning to guide segmentation. In: ICLR (2019)Google Scholar
  39. 39.
    Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: Meta-learning with memory-augmented neural networks. In: ICML (2016)Google Scholar
  40. 40.
    Shankar Nagaraja, N., Schmidt, F.R., Brox, T.: Video segmentation with just a few strokes. In: ICCV (2015)Google Scholar
  41. 41.
    Siam, M., et al.: Video segmentation using teacher-student adaptation in a human robot interaction (HRI) setting. In: ICRA (2019)Google Scholar
  42. 42.
    Song, H., Wang, W., Zhao, S., Shen, J., Lam, K.-M.: Pyramid dilated deeper ConvLSTM for video salient object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 744–760. Springer, Cham (2018). Scholar
  43. 43.
    Sukhbaatar, S., Szlam, A., Weston, J., Fergus, R.: End-to-end memory networks. In: NIPS (2015)Google Scholar
  44. 44.
    Tokmakov, P., Alahari, K., Schmid, C.: Learning motion patterns in videos. In: CVPR (2017)Google Scholar
  45. 45.
    Tokmakov, P., Alahari, K., Schmid, C.: Learning video object segmentation with visual memory. In: ICCV (2017)Google Scholar
  46. 46.
    Tokmakov, P., Schmid, C., Alahari, K.: Learning to segment moving objects. IJCV 127(3), 282–301 (2019)CrossRefGoogle Scholar
  47. 47.
    Tsai, Y.-H., Zhong, G., Yang, M.-H.: Semantic co-segmentation in videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 760–775. Springer, Cham (2016). Scholar
  48. 48.
    Ventura, C., Bellver, M., Girbau, A., Salvador, A., Marques, F., Giro-i Nieto, X.: RVOS: end-to-end recurrent network for video object segmentation. In: CVPR (2019)Google Scholar
  49. 49.
    Voigtlaender, P., Chai, Y., Schroff, F., Adam, H., Leibe, B., Chen, L.C.: FEELVOS: fast end-to-end embedding learning for video object segmentation. In: CVPR (2019)Google Scholar
  50. 50.
    Voigtlaender, P., Leibe, B.: Online adaptation of convolutional neural networks for video object segmentation. In: BMVC (2017)Google Scholar
  51. 51.
    Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: CVPR (2019)Google Scholar
  52. 52.
    Wang, W., Lu, X., Shen, J., Crandall, D.J., Shao, L.: Zero-shot video object segmentation via attentive graph neural networks. In: ICCV (2019)Google Scholar
  53. 53.
    Wang, W., Shen, J., Porikli, F., Yang, R.: Semi-supervised video object segmentation with super-trajectories. IEEE TPAMI 41(4), 985–998 (2018)CrossRefGoogle Scholar
  54. 54.
    Wang, W., Shen, J., Yang, R., Porikli, F.: Saliency-aware video object segmentation. IEEE TPAMI 40(1), 20–33 (2017)CrossRefGoogle Scholar
  55. 55.
    Wang, W., et al.: Learning unsupervised video object segmentation through visual attention. In: CVPR (2019)Google Scholar
  56. 56.
    Wang, Z., Xu, J., Liu, L., Zhu, F., Shao, L.: Ranet: Ranking attention network for fast video object segmentation. In: ICCV (2019)Google Scholar
  57. 57.
    Wen, L., Du, D., Lei, Z., Li, S.Z., Yang, M.H.: JOTS: joint online tracking and segmentation. In: CVPR (2015)Google Scholar
  58. 58.
    Weston, J., Chopra, S., Bordes, A.: Memory networks. ICLR (2015)Google Scholar
  59. 59.
    Wug Oh, S., Lee, J.Y., Sunkavalli, K., Joo Kim, S.: Fast video object segmentation by reference-guided mask propagation. In: CVPR (2018)Google Scholar
  60. 60.
    Xiao, H., Feng, J., Lin, G., Liu, Y., Zhang, M.: MoNet: deep motion exploitation for video object segmentation. In: CVPR (2018)Google Scholar
  61. 61.
    Xiao, H., Kang, B., Liu, Y., Zhang, M., Feng, J.: Online meta adaptation for fast video object segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 42, 1205–1217 (2019)Google Scholar
  62. 62.
    Xie, G.S., et al.: Attentive region embedding network for zero-shot learning. In: CVPR (2019)Google Scholar
  63. 63.
    Xie, G.S., et al.: Region graph embedding network for zero-shot learning. In: ECCV (2020)Google Scholar
  64. 64.
    Xu, N., et al.: YouTube-VOS: sequence-to-sequence video object segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 603–619. Springer, Cham (2018). Scholar
  65. 65.
    Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.: Saliency detection via graph-based manifold ranking. In: CVPR (2013)Google Scholar
  66. 66.
    Yang, L., Wang, Y., Xiong, X., Yang, J., Katsaggelos, A.K.: Efficient video object segmentation via network modulation. In: CVPR (2018)Google Scholar
  67. 67.
    Yang, T., Chan, A.B.: Learning dynamic memory networks for object tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 153–169. Springer, Cham (2018). Scholar
  68. 68.
    Yang, Z., Wang, Q., Bertinetto, L., Bai, S., Hu, W., Torr, P.H.: Anchor diffusion for unsupervised video object segmentation. In: ICCV (2019)Google Scholar
  69. 69.
    Yoon, J.S., Rameau, F., Kim, J., Lee, S., Shin, S., Kweon, I.S.: Pixel-level matching for video object segmentation using convolutional neural networks. In: ICCV (2017)Google Scholar
  70. 70.
    Zeng, X., Liao, R., Gu, L., Xiong, Y., Fidler, S., Urtasun, R.: DMM-Net: differentiable mask-matching network for video object segmentation. In: ICCV (2019)Google Scholar
  71. 71.
    Zhang, D., Javed, O., Shah, M.: Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. In: CVPR (2013)Google Scholar
  72. 72.
    Zhou, T., Wang, S., Zhou, Y., Yao, Y., Li, J., Shao, L.: Motion-attentive transition for zero-shot video object segmentation. In: AAAI (2020)Google Scholar
  73. 73.
    Zhuo, T., Cheng, Z., Zhang, P., Wong, Y., Kankanhalli, M.: Unsupervised online video object segmentation with motion property understanding. IEEE TIP 29, 237–249 (2019)MathSciNetGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Inception Institute of Artificial IntelligenceAbu DhabiUAE
  2. 2.ETH ZurichZürichSwitzerland

Personalised recommendations