Barlow Twins: Self-Supervised Learning via Redundancy Reduction
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.
Code (24)
Tasks
General ClassificationImage ClassificationObject DetectionSelf-Supervised Image ClassificationSelf-Supervised LearningSemi-Supervised Image ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DinoTwins: Combining DINO and Barlow Twins for Robust, Label-Efficient Vision Transformers
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 SegmentationUnderstanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction
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 IdentificationSelf-Supervised Learning by Curvature Alignment
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 LearningBarlow Graph Auto-Encoder for Unsupervised Network Embedding
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+1Audio Barlow Twins: Self-Supervised Audio Representation Learning
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