paper-with-me

홈 › Papers

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, Chang D. Yoo, In So Kweon

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 has attracted significant attention for providing a minimalist simple Siamese (SimSiam) method to avoid collapse. However, the reason for how it avoids collapse without negative samples remains not fully clear and our investigation starts by revisiting the explanatory claims in the original SimSiam. After refuting their claims, we introduce vector decomposition for analyzing the collapse based on the gradient analysis of the $l_2$-normalized representation vector. This yields a unified perspective on how negative samples and SimSiam alleviate collapse. Such a unified perspective comes timely for understanding the recent progress in SSL.

📄 PDF Abstract BibTeX arXiv:2203.16262

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningSelf-Supervised Learning

Similar Papers 제목 키워드 기반

How Does SimSiam Avoid Collapse Without Negative Samples? Towards a Unified Understanding of Progress in SSL

2021-09-29 · ICLR 2022 4 · Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Trung X. Pham 외

Towards avoiding collapse in self-supervised learning (SSL), contrastive loss is widely used but often requires a large number of negative samples. Without negative samples yet achieving competitive performance one recen…

Self-Supervised Learning

Understanding Collapse in Non-Contrastive Siamese Representation Learning

2022-09-29 · Alexander C. Li, Alexei A. Efros, Deepak Pathak

Contrastive methods have led a recent surge in the performance of self-supervised representation learning (SSL). Recent methods like BYOL or SimSiam purportedly distill these contrastive methods down to their essence, re…

Continual LearningContrastive LearningRepresentation Learning

Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics

2023-09-28 · Han Bao

Contrastive learning is a self-supervised representation learning framework, where two positive views generated through data augmentation are made similar by an attraction force in a data representation space, while a re…

Computational EfficiencyContrastive LearningData AugmentationRepresentation Learning

Implicit variance regularization in non-contrastive SSL

2022-12-09 · NeurIPS 2023 11 · Manu Srinath Halvagal, Axel Laborieux, Friedemann Zenke

Non-contrastive SSL methods like BYOL and SimSiam rely on asymmetric predictor networks to avoid representational collapse without negative samples. Yet, how predictor networks facilitate stable learning is not fully und…

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…

Self-Supervised Learning