The reviewed record of science sign in
Pith

arxiv: 2206.07692 · v1 · pith:RB6B56HB · submitted 2022-06-15 · cs.CV

A Simple Data Mixing Prior for Improving Self-Supervised Learning

Reviewed by Pithpith:RB6B56HBopen to challenge →

classification cs.CV
keywords self-supervisedtextbfdatamixingsdmpimageslearningessential
0
0 comments X
read the original abstract

Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images that share the same source images are intrinsically related to each other, we hereby propose SDMP, short for $\textbf{S}$imple $\textbf{D}$ata $\textbf{M}$ixing $\textbf{P}$rior, to capture this straightforward yet essential prior, and position such mixed images as additional $\textbf{positive pairs}$ to facilitate self-supervised representation learning. Our experiments verify that the proposed SDMP enables data mixing to help a set of self-supervised learning frameworks (e.g., MoCo) achieve better accuracy and out-of-distribution robustness. More notably, our SDMP is the first method that successfully leverages data mixing to improve (rather than hurt) the performance of Vision Transformers in the self-supervised setting. Code is publicly available at https://github.com/OliverRensu/SDMP

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.