paper-with-me

홈 › Papers

Understanding self-supervised Learning Dynamics without Contrastive Pairs

2021-02-12 · Yuandong Tian, Xinlei Chen, Surya Ganguli

While contrastive approaches of self-supervised learning (SSL) learn representations by minimizing the distance between two augmented views of the same data point (positive pairs) and maximizing views from different data points (negative pairs), recent \emph{non-contrastive} SSL (e.g., BYOL and SimSiam) show remarkable performance {\it without} negative pairs, with an extra learnable predictor and a stop-gradient operation. A fundamental question arises: why do these methods not collapse into trivial representations? We answer this question via a simple theoretical study and propose a novel approach, DirectPred, that \emph{directly} sets the linear predictor based on the statistics of its inputs, without gradient training. On ImageNet, it performs comparably with more complex two-layer non-linear predictors that employ BatchNorm and outperforms a linear predictor by $2.5\%$ in 300-epoch training (and $5\%$ in 60-epoch). DirectPred is motivated by our theoretical study of the nonlinear learning dynamics of non-contrastive SSL in simple linear networks. Our study yields conceptual insights into how non-contrastive SSL methods learn, how they avoid representational collapse, and how multiple factors, like predictor networks, stop-gradients, exponential moving averages, and weight decay all come into play. Our simple theory recapitulates the results of real-world ablation studies in both STL-10 and ImageNet. Code is released https://github.com/facebookresearch/luckmatters/tree/master/ssl.

📄 PDF Abstract BibTeX arXiv:2102.06810

Code (5)

facebookresearch/luckmatters 공식 구현 pytorch
facebookresearch/luckmatters/tree/master/ssl 공식 구현 pytorch
fmi-basel/implicit-var-reg pytorch
lucidrains/byol-pytorch pytorch
miszkur/SelfSupervisedLearning tf

Tasks

Self-Supervised Learning

Methods 이 논문이 사용한 방법론

BYOL 설명 없음
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Understanding Dimensional Collapse in Contrastive Self-supervised Learning

2021-10-18 · ICLR 2022 4 · Li Jing, Pascal Vincent, Yann Lecun, Yuandong Tian

Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. Joint embedding approach bases on maximizing the agreement between embedding vectors from differen…

Contrastive LearningLearning TheoryRepresentation LearningSelf-Supervised Learning

A Message Passing Perspective on Learning Dynamics of Contrastive Learning

2023-03-08 · Yifei Wang, Qi Zhang, Tianqi Du, Jiansheng Yang 외

In recent years, contrastive learning achieves impressive results on self-supervised visual representation learning, but there still lacks a rigorous understanding of its learning dynamics. In this paper, we show that if…

Contrastive LearningGraph AttentionRepresentation Learning

How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning

2022-03-30 · Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Trung X. Pham 외

To avoid collapse in self-supervised learning (SSL), a contrastive loss is widely used but often requires a large number of negative samples. Without negative samples yet achieving competitive performance, a recent work …

Contrastive LearningSelf-Supervised Learning

A Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis

2025-03-14 · Asifullah Khan, Laiba Asmatullah, Anza Malik, Shahzaib Khan 외

Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive lear…

Contrastive LearningSelf-Supervised Learning

Pose-disentangled Contrastive Learning for Self-supervised Facial Representation

2022-11-24 · CVPR 2023 1 · Yuanyuan Liu, Wenbin Wang, Yibing Zhan, Shaoze Feng 외

Self-supervised facial representation has recently attracted increasing attention due to its ability to perform face understanding without relying on large-scale annotated datasets heavily. However, analytically, current…

Contrastive LearningData AugmentationDecoderFace Recognition+6