A simple data mixing prior for improving self-supervised learning
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 he...
Saved in:
Main Authors: | REN, Sucheng, WANG, Huiyu, GAO, Zhengqi, HE, Shengfeng, YUILLE, Alan, ZHOU, Yuyin, XIE, Cihang |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8445 https://ink.library.smu.edu.sg/context/sis_research/article/9448/viewcontent/Ren_A_Simple_Data_Mixing_Prior_for_Improving_Self_Supervised_Learning_CVPR_2022_paper.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Exploring object relation in mean teacher for cross-domain detection
by: CAI, Qi, et al.
Published: (2019) -
Meta-Transfer Learning for Few-Shot Learning
by: Qianru Sun, et al.
Published: (2020) -
R2GAN: Cross-modal recipe retrieval with generative adversarial network
by: ZHU, Bin, et al.
Published: (2019) -
Transferrable prototypical networks for unsupervised domain adaptation
by: PAN, Yingwei, et al.
Published: (2019) -
Learning to teach and learn for semi-supervised few-shot image classification
by: LI, Xinzhe, et al.
Published: (2021)