Skip to main content

Streaming Multiscale Deep Equilibrium Models

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

We present StreamDEQ, a method that infers frame-wise representations on videos with minimal per-frame computation. In contrast to conventional methods where compute time grows at least linearly with the network depth, we aim to update the representations in a continuous manner. For this purpose, we leverage the recently emerging implicit layer models, which infer the representation of an image by solving a fixed-point problem. Our main insight is to leverage the slowly changing nature of videos and use the previous frame representation as an initial condition on each frame. This scheme effectively recycles the recent inference computations and greatly reduces the needed processing time. Through extensive experimental analysis, we show that StreamDEQ is able to recover near-optimal representations in a few frames time, and maintain an up-to-date representation throughout the video duration. Our experiments on video semantic segmentation and video object detection show that StreamDEQ achieves on par accuracy with the baseline (standard MDEQ) while being more than \(3\times \) faster. Code and additional results are available at https://ufukertenli.github.io/streamdeq/.

E. Akbas and R. G. Cinbis—Equal contribution for senior authorship.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    We do not refer to a mathematical definition of smoothness, but rather emphasize that the changes between neighboring frames are small.

References

  1. Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: ICLR (2015)

    Google Scholar 

  2. Bai, S., Kolter, J.Z., Koltun, V.: Deep equilibrium models. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)

    Google Scholar 

  3. Bai, S., Kolter, J.Z., Koltun, V.: Trellis networks for sequence modeling. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=HyeVtoRqtQ

  4. Bai, S., Koltun, V., Kolter, J.Z.: Multiscale deep equilibrium models. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)

    Google Scholar 

  5. Bai, S., Koltun, V., Kolter, J.Z.: Neural deep equilibrium solvers. In: International Conference on Learning Representations (2021)

    Google Scholar 

  6. Bai, S., Koltun, V., Kolter, J.Z.: Stabilizing equilibrium models by jacobian regularization. In: International Conference on Machine Learning (ICML) (2021)

    Google Scholar 

  7. Bazzani, L., de Freitas, N., Larochelle, H., Murino, V., Ting, J.A.: Learning attentional policies for tracking and recognition in video with deep networks. In: ICML (2011)

    Google Scholar 

  8. Bertasius, G., Torresani, L., Shi, J.: Object detection in video with spatiotemporal sampling networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 331–346 (2018)

    Google Scholar 

  9. Broyden, C.G.: A class of methods for solving nonlinear simultaneous equations. Math. Comput. 19(92), 577–593 (1965)

    Article  MathSciNet  MATH  Google Scholar 

  10. Carreira, J., Patraucean, V., Mazare, L., Zisserman, A., Osindero, S.: Massively parallel video networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 649–666 (2018)

    Google Scholar 

  11. Chen, K., et al.: MMDetection: open MMlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)

  12. Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10337–10346 (2020)

    Google Scholar 

  13. Contributors, M.: MMTracking: OpenMMLab video perception toolbox and benchmark (2020). https://github.com/open-mmlab/mmtracking

  14. Cordonnier, J.B., et al.: Differentiable patch selection for image recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2351–2360 (2021)

    Google Scholar 

  15. Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)

    Google Scholar 

  16. Dehghani, M., Gouws, S., Vinyals, O., Uszkoreit, J., Kaiser, L.: Universal transformers. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=HyzdRiR9Y7

  17. Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., Mei, T.: Relation distillation networks for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7023–7032 (2019)

    Google Scholar 

  18. Denil, M., Bazzani, L., Larochelle, H., de Freitas, N.: Learning where to attend with deep architectures for image tracking. Neural Comput. 24(8), 2151–2184 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  19. Gadde, R., Jampani, V., Gehler, P.V.: Semantic video CNNs through representation warping. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4453–4462 (2017)

    Google Scholar 

  20. Han, W., et al.: SEQ-NMS for video object detection. arXiv preprint arXiv:1602.08465 (2016)

  21. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  22. Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)

    Article  MATH  Google Scholar 

  23. Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)

  24. Hu, P., Caba, F., Wang, O., Lin, Z., Sclaroff, S., Perazzi, F.: Temporally distributed networks for fast video semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8818–8827 (2020)

    Google Scholar 

  25. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)

    Google Scholar 

  26. Huang, P.Y., Hsu, W.T., Chiu, C.Y., Wu, T.F., Sun, M.: Efficient uncertainty estimation for semantic segmentation in videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 520–535 (2018)

    Google Scholar 

  27. Huang, Z., Bai, S., Kolter, J.Z.: \(\text{(Implicit)}^2\): Implicit layers for implicit representations. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)

    Google Scholar 

  28. Jain, S., Wang, X., Gonzalez, J.E.: Accel: a corrective fusion network for efficient semantic segmentation on video. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8866–8875 (2019)

    Google Scholar 

  29. Kang, K., et al.: T-CNN: tubelets with convolutional neural networks for object detection from videos. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2896–2907 (2017)

    Article  Google Scholar 

  30. Kang, K., Ouyang, W., Li, H., Wang, X.: Object detection from video tubelets with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 817–825 (2016)

    Google Scholar 

  31. Li, M., Wang, Y.-X., Ramanan, D.: Towards streaming perception. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 473–488. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_28

    Chapter  Google Scholar 

  32. Li, Y., Shi, J., Lin, D.: Low-latency video semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5997–6005 (2018)

    Google Scholar 

  33. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

    Google Scholar 

  34. Liu, M., Zhu, M.: Mobile video object detection with temporally-aware feature maps. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5686–5695 (2018)

    Google Scholar 

  35. Liu, M., Zhu, M., White, M., Li, Y., Kalenichenko, D.: Looking fast and slow: memory-guided mobile video object detection. arXiv preprint arXiv:1903.10172 (2019)

  36. Liu, Y., Shen, C., Yu, C., Wang, J.: Efficient semantic video segmentation with per-frame inference. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 352–368. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58607-2_21

    Chapter  Google Scholar 

  37. Liu, Z., Wang, H.J., Xu, Z., Darrell, T., Shelhamer, E.: Confidence adaptive anytime pixel-level recognition. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=kNKFOXleuC

  38. Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014). https://proceedings.neurips.cc/paper/2014/file/09c6c3783b4a70054da74f2538ed47c6-Paper.pdf

  39. Narayanan, D., et al.: PipeDream: generalized pipeline parallelism for DNN training. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles, pp. 1–15 (2019)

    Google Scholar 

  40. Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035. Curran Associates, Inc. (2019). https://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf

  41. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28, 1–9 (2015)

    Google Scholar 

  42. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y

    Article  MathSciNet  Google Scholar 

  43. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)

    Google Scholar 

  44. Shelhamer, E., Rakelly, K., Hoffman, J., Darrell, T.: Clockwork convnets for video semantic segmentation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 852–868. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_69

    Chapter  Google Scholar 

  45. Wang, S., Zhou, Y., Yan, J., Deng, Z.: Fully motion-aware network for video object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 542–557 (2018)

    Google Scholar 

  46. Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9217–9225 (2019)

    Google Scholar 

  47. Xu, Y.S., Fu, T.J., Yang, H.K., Lee, C.Y.: Dynamic video segmentation network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6556–6565 (2018)

    Google Scholar 

  48. Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)

  49. Zhao, B., Zhao, B., Tang, L., Han, Y., Wang, W.: Deep spatial-temporal joint feature representation for video object detection. Sensors 18(3), 774 (2018)

    Article  Google Scholar 

  50. Zhu, H., Wei, H., Li, B., Yuan, X., Kehtarnavaz, N.: A review of video object detection: datasets, metrics and methods. Appl. Sci. 10(21), 7834 (2020)

    Article  Google Scholar 

  51. Zhu, X., Dai, J., Yuan, L., Wei, Y.: Towards high performance video object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7210–7218 (2018)

    Google Scholar 

  52. Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 408–417 (2017)

    Google Scholar 

  53. Zhu, X., Xiong, Y., Dai, J., Yuan, L., Wei, Y.: Deep feature flow for video recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2349–2358 (2017)

    Google Scholar 

Download references

Acknowledgments

The numerical calculations were partially performed at TUBITAK ULAKBIM, High Performance and Grid Computing Center (TRUBA) and METU Robotics and AI Technologies Research Center (ROMER) resources. Dr. Cinbis is supported by a Google Faculty Research Award. Dr. Akbas is supported by the BAGEP Award of the Science Academy, Turkey.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Can Ufuk Ertenli .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 134 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ertenli, C.U., Akbas, E., Cinbis, R.G. (2022). Streaming Multiscale Deep Equilibrium Models. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13671. Springer, Cham. https://doi.org/10.1007/978-3-031-20083-0_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20083-0_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20082-3

  • Online ISBN: 978-3-031-20083-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics