Understanding self-supervised Learning Dynamics without Contrastive Pairs
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.
Code (5)
Tasks
Self-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Understanding Dimensional Collapse in Contrastive Self-supervised Learning
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 LearningA Message Passing Perspective on Learning Dynamics of Contrastive Learning
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 LearningHow Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning
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 LearningA Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis
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 LearningPose-disentangled Contrastive Learning for Self-supervised Facial Representation
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