Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yudong, Xie, Ruobing, Chen, Jiansheng, Sun, Xingwu, Kang, Zhanhui, Wang, Yu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909581024690176
author Zhang, Yudong
Xie, Ruobing
Chen, Jiansheng
Sun, Xingwu
Kang, Zhanhui
Wang, Yu
author_facet Zhang, Yudong
Xie, Ruobing
Chen, Jiansheng
Sun, Xingwu
Kang, Zhanhui
Wang, Yu
contents Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image. Designing effective data augmentation strategies is crucial for the success of contrastive learning. Inspired by the story of the blind men and the elephant, we introduce JointCrop and JointBlur. These methods generate more challenging positive pairs by leveraging the joint distribution of the two augmentation parameters, thereby enabling contrastive learning to acquire more effective feature representations. To the best of our knowledge, this is the first effort to explicitly incorporate the joint distribution of two data augmentation parameters into contrastive learning. As a plug-and-play framework without additional computational overhead, JointCrop and JointBlur enhance the performance of SimCLR, BYOL, MoCo v1, MoCo v2, MoCo v3, SimSiam, and Dino baselines with notable improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16522
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
Zhang, Yudong
Xie, Ruobing
Chen, Jiansheng
Sun, Xingwu
Kang, Zhanhui
Wang, Yu
Computer Vision and Pattern Recognition
Artificial Intelligence
Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image. Designing effective data augmentation strategies is crucial for the success of contrastive learning. Inspired by the story of the blind men and the elephant, we introduce JointCrop and JointBlur. These methods generate more challenging positive pairs by leveraging the joint distribution of the two augmentation parameters, thereby enabling contrastive learning to acquire more effective feature representations. To the best of our knowledge, this is the first effort to explicitly incorporate the joint distribution of two data augmentation parameters into contrastive learning. As a plug-and-play framework without additional computational overhead, JointCrop and JointBlur enhance the performance of SimCLR, BYOL, MoCo v1, MoCo v2, MoCo v3, SimSiam, and Dino baselines with notable improvements.
title Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.16522