paper-with-me

Papers

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

2021-03-04 · Jure Zbontar, Li Jing, Ishan Misra, Yann Lecun, Stéphane Deny

Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are invariant to distortions of the input sample. However, a recurring issue with this approach is the existence of trivial constant solutions. Most current methods avoid such solutions by careful implementation details. We propose an objective function that naturally avoids collapse by measuring the cross-correlation matrix between the outputs of two identical networks fed with distorted versions of a sample, and making it as close to the identity matrix as possible. This causes the embedding vectors of distorted versions of a sample to be similar, while minimizing the redundancy between the components of these vectors. The method is called Barlow Twins, owing to neuroscientist H. Barlow's redundancy-reduction principle applied to a pair of identical networks. Barlow Twins does not require large batches nor asymmetry between the network twins such as a predictor network, gradient stopping, or a moving average on the weight updates. Intriguingly it benefits from very high-dimensional output vectors. Barlow Twins outperforms previous methods on ImageNet for semi-supervised classification in the low-data regime, and is on par with current state of the art for ImageNet classification with a linear classifier head, and for transfer tasks of classification and object detection.

📄 PDF Abstract BibTeX arXiv:2103.03230

Code (24)

facebookresearch/barlowtwins 공식 구현 pytorch
FloCF/SSL_pytorch pytorch
GregorKobsik/Octree-Transformer pytorch
IgorSusmelj/barlowtwins pytorch
MaxLikesMath/Barlow-Twins-Pytorch pytorch
Pangoraw/GeoSSL pytorch
PaperCodeReview/BarlowTwins-TF tf
Westlake-AI/openmixup pytorch
beresandras/contrastive-classification-keras tf
facebookresearch/clip-rocket pytorch
facebookresearch/vissl pytorch
gaborvecsei/Barlow-Twins tf
gabrieldernbach/barlow-twins pytorch
jeffwiroj/robust_tutorial pytorch
jonahanton/ssl_audio pytorch
kalelpark/FG-SSL pytorch
leot13/BarlowTwins pytorch
lightly-ai/lightly pytorch
naver/tldr pytorch
open-mmlab/mmselfsup pytorch
sayakpaul/Barlow-Twins-TF tf
vturrisi/solo-learn pytorch
zcao0420/moformer pytorch
https://gitlab.com/birder/birder pytorch

Tasks

General ClassificationImage ClassificationObject DetectionSelf-Supervised Image ClassificationSelf-Supervised LearningSemi-Supervised Image Classification

Methods 이 논문이 사용한 방법론

Barlow Twins Barlow Twins is a self-supervised learning method that applies redundancy-reduction — a principle first proposed in neuroscience — to self supervised learning. The objective…

Similar Papers 제목 키워드 기반

DinoTwins: Combining DINO and Barlow Twins for Robust, Label-Efficient Vision Transformers

2025-08-24 · Michael Podsiadly, Brendon K Lay arxiv

Training AI models to understand images without costly labeled data remains a challenge. We combine two techniques--DINO (teacher-student learning) and Barlow Twins (redundancy reduction)--to create a model that learns b…

Self-Supervised LearningSemantic Segmentation

Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction

2023-09-07 · Yusuf Brima, Ulf Krumnack, Simone Pika, Gunther Heidemann

Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data. By designing pretext tasks that exploit statistical regularities, SSL models can captur…

Keyword SpottingSelf-Supervised LearningSpeaker Identification

Self-Supervised Learning by Curvature Alignment

2025-11-21 · Benyamin Ghojogh, M. Hadi Sepanj, Paul Fieguth arxiv

Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. While such objectives shape first- and sec…

Self-Supervised Learning

Barlow Graph Auto-Encoder for Unsupervised Network Embedding

2021-10-29 · Rayyan Ahmad Khan, Martin Kleinsteuber

Network embedding has emerged as a promising research field for network analysis. Recently, an approach, named Barlow Twins, has been proposed for self-supervised learning in computer vision by applying the redundancy-re…

Inductive Link PredictionLink PredictionNetwork EmbeddingNode Classification+1

Audio Barlow Twins: Self-Supervised Audio Representation Learning

2022-09-28 · Jonah Anton, Harry Coppock, Pancham Shukla, Bjorn W. Schuller

The Barlow Twins self-supervised learning objective requires neither negative samples or asymmetric learning updates, achieving results on a par with the current state-of-the-art within Computer Vision. As such, we prese…

Environmental Sound ClassificationEvent DetectionRepresentation LearningSelf-Supervised Learning