Skip to main content

Masked Siamese Networks for Label-Efficient Learning

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


We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containing randomly masked patches to the representation of the original unmasked image. This self-supervised pre-training strategy is particularly scalable when applied to Vision Transformers since only the unmasked patches are processed by the network. As a result, MSNs improve the scalability of joint-embedding architectures, while producing representations of a high semantic level that perform competitively on low-shot image classification. For instance, on ImageNet-1K, with only 5,000 annotated images, our base MSN model achieves 72.4% top-1 accuracy, and with 1% of ImageNet-1K labels, we achieve 75.7% top-1 accuracy, setting a new state-of-the-art for self-supervised learning on this benchmark. Our code is publicly available at

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

Access this chapter

USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
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


  1. 1.

    Note that the performance of the ViT-S/16 can be improved by removing the Sinkhorn normalization, as we do in Table 2, however for consistency of evaluation with other models, we keep it in for this ablation.


  1. Assran, M., et al.: Semi-supervised learning of visual features by non-parametrically predicting view assignments with support samples. In: ICCV (2021)

    Google Scholar 

  2. Atito, S., Awais, M., Kittler, J.: SiT: self-supervised vision transformer. arXiv preprint arXiv:2104.03602 (2021)

  3. Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. arXiv preprint arXiv:2202.03555 (2022)

  4. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)

  5. Bao, H., Dong, L., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)

  6. Bardes, A., Ponce, J., LeCun, Y.: VICReg: variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906 (2021)

  7. Becker, S., Hinton, G.E.: Self-organizing neural network that discovers surfaces in random-dot stereograms. Nature 355(6356), 161–163 (1992)

    Article  Google Scholar 

  8. Bordes, F., Balestriero, R., Vincent, P.: High fidelity visualization of what your self-supervised representation knows about. arXiv preprint arXiv:2112.09164 (2021)

  9. Bromley, J., et al.: Signature verification using a “Siamese’’ time delay neural network. Int. J. Pattern Recognit Artif Intell. 7(04), 669–688 (1993)

    Article  Google Scholar 

  10. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)

    Google Scholar 

  11. Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)

    Google Scholar 

  12. Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691–1703. PMLR (2020)

    Google Scholar 

  13. Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. preprint arXiv:2002.05709 (2020)

  14. Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.: Big self-supervised models are strong semi-supervised learners. arXiv preprint arXiv:2006.10029 (2020)

  15. Chen, X., He, K.: Exploring simple Siamese representation learning. arXiv preprint arXiv:2011.10566 (2020)

  16. Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. arXiv preprint arXiv:2104.02057 (2021)

  17. Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: CVPR (2019)

    Google Scholar 

  18. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)

  19. Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1422–1430 (2015)

    Google Scholar 

  20. Donahue, J., Simonyan, K.: Large scale adversarial representation learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)

    Google Scholar 

  21. Dosovitskiy, A., et al.: An image is worth 16\(\times \)16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)

  22. Dosovitskiy, A., Springenberg, J.T., Riedmiller, M.A., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. CoRR (2014)

    Google Scholar 

  23. El-Nouby, A., Izacard, G., Touvron, H., Laptev, I., Jegou, H., Grave, E.: Are large-scale datasets necessary for self-supervised pre-training? arXiv preprint arXiv:2112.10740 (2021)

  24. Goyal, P., Mahajan, D., Gupta, A., Misra, I.: Scaling and benchmarking self-supervised visual representation learning. In: ICCV (2019)

    Google Scholar 

  25. Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: NeurIPS (2020)

    Google Scholar 

  26. Gupta, K., Somepalli, G., Anubhav, A., Magalle Hewa, V.Y.J., Zwicker, M., Shrivastava, A.: PatchGame: learning to signal mid-level patches in referential games. In: Advances in Neural Information Processing Systems, vol. 34, pp. 26015–26027 (2021)

    Google Scholar 

  27. He, K., Chen, X., Xie, S., Li, Y., Dollár, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)

  28. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:1911.05722 (2019)

  29. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  30. Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: ICCV (2021)

    Google Scholar 

  31. Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of the International Conference on Learning Representations (2019)

    Google Scholar 

  32. Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: CVPR (2021)

    Google Scholar 

  33. Joulin, A., Bach, F.: A convex relaxation for weakly supervised classifiers. arXiv preprint arXiv:1206.6413 (2012)

  34. Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: ECCV (2016)

    Google Scholar 

  35. Larsson, G., Maire, M., Shakhnarovich, G.: Colorization as a proxy task for visual understanding. In: CVPR (2017)

    Google Scholar 

  36. Li, C., et al.: Efficient self-supervised vision transformers for representation learning. arXiv preprint arXiv:2106.09785 (2021)

  37. Li, Z., et al.: MST: masked self-supervised transformer for visual representation. Adv. Neural. Inf. Process. Syst. 34, 13165–13176 (2021)

    Google Scholar 

  38. Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)

  39. Lucas, T., Weinzaepfel, P., Rogez, G.: Barely-supervised learning: semi-supervised learning with very few labeled images. preprint arXiv:2112.12004 (2021)

  40. Mairal, J.: Cyanure: an open-source toolbox for empirical risk minimization for Python, C++, and soon more. arXiv preprint arXiv:1912.08165 (2019)

  41. Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: CVPR (2020)

    Google Scholar 

  42. Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by Solving Jigsaw Puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69–84. Springer, Cham (2016).

    Chapter  Google Scholar 

  43. Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)

    Google Scholar 

  44. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)

    Article  MathSciNet  Google Scholar 

  45. Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685 (2020)

  46. Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776–794. Springer, Cham (2020).

    Chapter  Google Scholar 

  47. Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jégou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347–10357. PMLR (2021)

    Google Scholar 

  48. Trinh, T.H., Luong, M.T., Le, Q.V.: Selfie: self-supervised pretraining for image embedding. arXiv preprint arXiv:1906.02940 (2019)

  49. Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)

    Google Scholar 

  50. Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A., Bottou, L.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(12) (2010)

    Google Scholar 

  51. Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, pp. 10506–10518 (2019)

    Google Scholar 

  52. Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. arXiv preprint arXiv:2112.09133 (2021)

  53. Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)

    Google Scholar 

  54. Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation. arXiv preprint arXiv:1904.12848 (2019)

  55. Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. arXiv preprint arXiv:2111.09886 (2021)

  56. Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: ICCV (2019)

    Google Scholar 

  57. Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. arXiv preprint arXiv:2103.03230 (2021)

  58. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)

  59. Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649–666. Springer, Cham (2016).

    Chapter  Google Scholar 

  60. Zhang, R., Isola, P., Efros, A.A.: Split-brain autoencoders: unsupervised learning by cross-channel prediction. In: CVPR (2017)

    Google Scholar 

  61. Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)

  62. Zhu, R., Zhao, B., Liu, J., Sun, Z., Chen, C.W.: Improving contrastive learning by visualizing feature transformation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10306–10315 (2021)

    Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Mahmoud Assran .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 6561 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

Assran, M. et al. (2022). Masked Siamese Networks for Label-Efficient Learning. 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 13691. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19820-5

  • Online ISBN: 978-3-031-19821-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics