Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

5-2023

Abstract

For unsupervised pretraining, mask-reconstruction pretraining (MRP) approaches, e.g. MAE (He et al., 2021) and data2vec (Baevski et al., 2022), randomly mask input patches and then reconstruct the pixels or semantic features of these masked patches via an auto-encoder. Then for a downstream task, supervised fine-tuning the pretrained encoder remarkably surpasses the conventional “supervised learning" (SL) trained from scratch. However, it is still unclear 1) how MRP performs semantic feature learning in the pretraining phase and 2) why it helps in downstream tasks. To solve these problems, we first theoretically show that on an auto-encoder of a two/one-layered convolution encoder/decoder, MRP can capture all discriminative features of each potential semantic class in the pretraining dataset. Then considering the fact that the pretraining dataset is of huge size and high diversity and thus covers most features in downstream dataset, in fine-tuning phase, the pretrained encoder can capture as much features as it can in downstream datasets, and would not lost these features with theoretical guarantees. In contrast, SL only randomly captures some features due to lottery ticket hypothesis. So MRP provably achieves better performance than SL on the classification tasks. Experimental results testify to our data assumptions and also our theoretical implications.

Discipline

Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 11th International Conference on Learning Representations ICLR 2023: Kigali, Rwanda, May 1-5

First Page

1

Last Page

48

Publisher

ICLR

City or Country

Kigali, Rwanda

Additional URL

https://openreview.net/forum?id=PaEUQiY40Dk

Download

Share

COinS