Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2022
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 Simple Data Mixing Prior, to capture this straightforward yet essential prior, and position such mixed images as additional 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.
Keywords
Categorization, Representation learning, Retrieval, Self- & semi- & meta- recognition, Detection
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces
Research Areas
Information Systems and Management; Intelligent Systems and Optimization
Publication
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR)
First Page
14575
Last Page
14584
ISBN
9781665469463
Identifier
10.1109/CVPR52688.2022.01419
Publisher
IEEE
City or Country
Canada
Citation
REN, Sucheng; WANG, Huiyu; GAO, Zhengqi; HE, Shengfeng; YUILLE, Alan; ZHOU, Yuyin; and XIE, Cihang.
A simple data mixing prior for improving self-supervised learning. (2022). Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR). 14575-14584.
Available at: https://ink.library.smu.edu.sg/sis_research/8445
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Included in
Databases and Information Systems Commons, Graphics and Human Computer Interfaces Commons