Abstract
In this work, we investigate approaches to leverage self-distillation via predictions consistency on self-supervised monocular depth estimation models. Since per-pixel depth predictions are not equally accurate, we propose a mechanism to filter out unreliable predictions. Moreover, we study representative strategies to enforce consistency between predictions. Our results show that choosing proper filtering and consistency enforcement approaches are key to obtain larger improvements on monocular depth estimation. Our method achieves competitive performance on the KITTI benchmark.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Athiwaratkun, B., Finzi, M., Izmailov, P., Wilson, A.G.: There are many consistent explanations of unlabeled data: why you should average. In: International Conference on Learning Representations (2019)
Casser, V., Pirk, S., Mahjourian, R., Angelova, A.: Depth prediction without the sensors: leveraging structure for unsupervised learning from monocular videos. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 8001–8008 (2019)
Chen, Y., Schmid, C., Sminchisescu, C.: Self-supervised learning with geometric constraints in monocular video: connecting flow, depth, and camera. In: IEEE International Conference on Computer Vision, pp. 7063–7072 (2019)
Cho, J., Min, D., Kim, Y., Sohn, K.: Deep monocular depth estimation leveraging a large-scale outdoor stereo dataset. Expert Syst. Appl. 178, 114877 (2021)
Choi, H., et al.: Adaptive confidence thresholding for monocular depth estimation. In: IEEE/CVF International Conference on Computer Vision, pp. 12808–12818 (2021)
Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in Neural Information Processing Systems, pp. 2366–2374 (2014)
Fang, Z., Chen, X., Chen, Y., Gool, L.V.: Towards good practice for CNN-based monocular depth estimation. In: IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1091–1100 (2020)
Furlanello, T., Lipton, Z., Tschannen, M., Itti, L., Anandkumar, A.: Born again neural networks. In: International Conference on Machine Learning, pp. 1607–1616. PMLR (2018)
Garg, R., Bg, V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 740–756. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_45
Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231–1237 (2013)
Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth prediction. In: International Conference on Computer Vision, October 2019
Gordon, A., Li, H., Jonschkowski, R., Angelova, A.: Depth from videos in the wild: unsupervised monocular depth learning from unknown cameras. arXiv preprint arXiv:1904.04998 (2019)
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407 (2018)
Kaushik, V., Jindgar, K., Lall, B.: ADAADepth: adapting data augmentation and attention for self-supervised monocular depth estimation. arXiv preprint arXiv:2103.00853 (2021)
Liu, L., Song, X., Wang, M., Liu, Y., Zhang, L.: Self-supervised monocular depth estimation for all day images using domain separation. In: IEEE/CVF International Conference on Computer Vision, pp. 12737–12746 (2021)
Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5667–5675 (2018)
Mendoza, J., Pedrini, H.: Adaptive self-supervised depth estimation in monocular videos. In: Peng, Y., Hu, S.-M., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds.) ICIG 2021. LNCS, vol. 12890, pp. 687–699. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87361-5_56
Mobahi, H., Farajtabar, M., Bartlett, P.: Self-distillation amplifies regularization in Hilbert space. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 3351–3361. Curran Associates, Inc. (2020)
Peng, R., Wang, R., Lai, Y., Tang, L., Cai, Y.: Excavating the potential capacity of self-supervised monocular depth estimation. In: IEEE International Conference on Computer Vision (2021)
Sajjadi, M., Javanmardi, M., Tasdizen, T.: Regularization with stochastic transformations and perturbations for deep semi-supervised learning. In: Advances in Neural Information Processing Systems, vol. 29, pp. 1163–1171 (2016)
Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)
Tonioni, A., Poggi, M., Mattoccia, S., Di Stefano, L.: Unsupervised domain adaptation for depth prediction from images. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2396–2409 (2019)
Xie, Q., Dai, Z., Hovy, E., Luong, T., Le, Q.: Unsupervised data augmentation for consistency training. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Xu, H., et al.: Digging into uncertainty in self-supervised multi-view stereo. In: IEEE/CVF International Conference on Computer Vision, pp. 6078–6087 (2021)
Xu, T.B., Liu, C.L.: Data-distortion guided self-distillation for deep neural networks. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 5565–5572 (2019)
Yang, C., Xie, L., Su, C., Yuille, A.L.: Snapshot distillation: teacher-student optimization in one generation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2859–2868 (2019)
Yang, J., Alvarez, J.M., Liu, M.: Self-supervised learning of depth inference for multi-view stereo. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7526–7534 (2021)
Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1851–1858 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Mendoza, J., Pedrini, H. (2022). Self-distilled Self-supervised Depth Estimation in Monocular Videos. In: El Yacoubi, M., Granger, E., Yuen, P.C., Pal, U., Vincent, N. (eds) Pattern Recognition and Artificial Intelligence. ICPRAI 2022. Lecture Notes in Computer Science, vol 13363. Springer, Cham. https://doi.org/10.1007/978-3-031-09037-0_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-09037-0_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09036-3
Online ISBN: 978-3-031-09037-0
eBook Packages: Computer ScienceComputer Science (R0)