Mean Shift for Self-Supervised Learning
Most recent self-supervised learning (SSL) algorithms learn features by contrasting between instances of images or by clustering the images and then contrasting between the image clusters. We introduce a simple mean-shift algorithm that learns representations by grouping images together without contrasting between them or adopting much of prior on the structure of the clusters. We simply "shift" the embedding of each image to be close to the "mean" of its neighbors. Since in our setting, the closest neighbor is always another augmentation of the same image, our model will be identical to BYOL when using only one nearest neighbor instead of 5 as used in our experiments. Our model achieves 72.4% on ImageNet linear evaluation with ResNet50 at 200 epochs outperforming BYOL. Our code is available here: https://github.com/UMBCvision/MSF
Code (1)
Tasks
ClusteringLinear evaluationSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning
We are interested in representation learning in self-supervised, supervised, and semi-supervised settings. Some recent self-supervised learning methods like mean-shift (MSF) cluster images by pulling the embedding of a q…
Pseudo LabelRepresentation LearningSelf-Supervised LearningCan Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?
Self-supervised learning in computer vision aims to leverage the inherent structure and relationships within data to learn meaningful representations without explicit human annotation, enabling a holistic understanding o…
Contrastive LearningKnowledge DistillationRepresentation LearningSelf-Supervised LearningSymbol-Temporal Consistency Self-supervised Learning for Robust Time Series Classification
The surge in the significance of time series in digital health domains necessitates advanced methodologies for extracting meaningful patterns and representations. Self-supervised contrastive learning has emerged as a pro…
Time Series ClassificationSelf-Supervised LearningContrastive LearningCrossNorm and SelfNorm for Generalization under Distribution Shifts
Traditional normalization techniques (e.g., Batch Normalization and Instance Normalization) generally and simplistically assume that training and test data follow the same distribution. As distribution shifts are inevita…
Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action pro…
RelationSelf-Supervised LearningSemi-Supervised Action DetectionTemporal Action Localization