paper-with-me

Papers

Mean Shift for Self-Supervised Learning

2021-05-15 · ICCV 2021 10 · Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash

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

📄 PDF Abstract BibTeX arXiv:2105.07269

Code (1)

UMBCvision/MSF 공식 구현 pytorch

Tasks

ClusteringLinear evaluationSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

BYOL 설명 없음

Similar Papers 제목 키워드 기반

Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning

2021-12-08 · KL Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Kossar Pourahmadi 외

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 Learning

Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?

2023-07-31 · Prakash Chandra Chhipa, Johan Rodahl Holmgren, Kanjar De, Rajkumar Saini 외

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 Learning

Symbol-Temporal Consistency Self-supervised Learning for Robust Time Series Classification

2025-09-24 · Kevin Garcia, Cassandra Garza, Brooklyn Berry, Yifeng Gao arxiv

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 Learning

CrossNorm and SelfNorm for Generalization under Distribution Shifts

2021-02-04 · ICCV 2021 10 · Zhiqiang Tang, Yunhe Gao, Yi Zhu, Zhi Zhang 외

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

2021-04-07 · CVPR 2021 1 · Xiang Wang, Shiwei Zhang, Zhiwu Qing, Yuanjie Shao 외

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