English

Masked Siamese Networks for Label-Efficient Learning

Machine Learning 2022-04-15 v1 Artificial Intelligence Computer Vision and Pattern Recognition Image and Video Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2204.07141,
  title  = {Masked Siamese Networks for Label-Efficient Learning},
  author = {Mahmoud Assran and Mathilde Caron and Ishan Misra and Piotr Bojanowski and Florian Bordes and Pascal Vincent and Armand Joulin and Michael Rabbat and Nicolas Ballas},
  journal= {arXiv preprint arXiv:2204.07141},
  year   = {2022}
}
R2 v1 2026-06-24T10:48:31.483Z