Masked Siamese ConvNets: Towards an Effective Masking Strategy for General-purpose Siamese Networks

Li Jing, Jiachen Zhu, Yann LeCun

Keywords: self-supervised learning, siamese networks, masking, convNets

TL;DR: We propose a masking strategy for siamese networks with ConvNets.

Abstract: Siamese Networks are a popular self-supervised learning framework that learns useful representation without human supervision by encouraging representations to be invariant to distortions. Existing methods heavily rely on hand-crafted augmentations, which are not easily adapted to new domains. To explore a general-purpose or domain-agnostic siamese network, we investigate using masking as augmentations in siamese networks. Recently, masking for siamese networks has only been shown useful with transformer architectures, e.g. MSN and data2vec. In this work, we identify the underlying problems of masking for siamese networks with arbitrary backbones, including ConvNets. We propose an effective and general-purpose masking strategy and demonstrate its effectiveness on various siamese network frameworks. Our method generally improves siamese networks' performances in the few-shot image classification, and object detection tasks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning