Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

Siyuan Li, Di Wu, Fang Wu, Zelin Zang, Lei Shang, Baigui Sun, Xuansong Xie, Stan Z. Li

Keywords: Self-supervised Learning, Vision Transformer, Representation Learning, Unsupervised Learning

TL;DR: We delve deep into masked image modeling (MIM) working mechanism and propose a generic pre-training framework (A$^2$MIM) for Transformers and CNNs.

Abstract: Masked image modeling (MIM), an emerging self-supervised pre-training method, has shown impressive success across numerous downstream vision tasks with Vision transformers (ViTs). Its underlying idea is simple: a portion of the input image is randomly masked out and then reconstructed via the pre-text task. However, the working principle behind MIM is not well explained, and previous studies insist that MIM primarily works for the Transformer family but is incompatible with CNNs. In this paper, we first study interactions among patches to understand what knowledge is learned and how it is acquired via the MIM task. We observe that MIM essentially teaches the model to learn better middle-order interactions among patches and extract more generalized features. Based on this fact, we propose an Architecture-Agnostic Masked Image Modeling framework (A$^2$MIM), which is compatible with both Transformers and CNNs in a unified way. Extensive experiments on popular benchmarks show that our A$^2$MIM learns better representations without explicit design and endows the backbone model with the stronger capability to transfer to various downstream tasks for both Transformers and CNNs.

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

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/architecture-agnostic-masked-image-modeling/code)