相关论文: The Mechanism of Prediction Head in Non-contrastiv…

Non-contrastive methods of self-supervised learning (such as BYOL and SimSiam) learn representations by minimizing the distance between two views of the same image. These approaches have achieved remarkable performance in practice, but the…

An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…

Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation. From an augmented view of an image, BYOL trains an online network to predict a target network representation of a different augmented view of…

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 points (negative…

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 repulsive force makes…

Labeling data is often very time consuming and expensive, leaving us with a majority of unlabeled data. Self-supervised representation learning methods such as SimCLR (Chen et al., 2020) or BYOL (Grill et al., 2020) have been very…

Heterogeneous graph neural networks can represent information of heterogeneous graphs with excellent ability. Recently, self-supervised learning manner is researched which learns the unique expression of a graph through a contrastive…

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an…

Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the representation space, or…

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

Self-predictive unsupervised learning methods such as BYOL or SimSiam have shown impressive results, and counter-intuitively, do not collapse to trivial representations. In this work, we aim at exploring the simplest possible mathematical…

Contrastive Learning (CL) has emerged as a powerful method for training feature extraction models using unlabeled data. Recent studies suggest that incorporating a linear projection head post-backbone significantly enhances model…

The representation learning problem in the oil & gas industry aims to construct a model that provides a representation based on logging data for a well interval. Previous attempts are mainly supervised and focus on similarity task, which…

In self-supervised representation learning, Siamese networks are a natural architecture for learning transformation-invariance by bringing representations of positive pairs closer together. But it is prone to collapse into a degenerate…

In this work, we have worked towards two major goals. Firstly, we have investigated the importance of Batch Normalisation (BN) layers in a non-contrastive representation learning framework called Bootstrap Your Own Latent (BYOL). We…

Transformations in the input space of Deep Neural Networks (DNN) lead to unintended changes in the feature space. Almost perceptually identical inputs, such as adversarial examples, can have significantly distant feature representations. On…

Bootstrap Your Own Latent (BYOL) introduced an approach to self-supervised learning avoiding the contrastive paradigm and subsequently removing the computational burden of negative sampling associated with such methods. However, we…

Self-supervised learning of deep neural networks has become a prevalent paradigm for learning representations that transfer to a variety of downstream tasks. Similar to proposed models of the ventral stream of biological vision, it is…

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

In recent years, self-supervised learning (SSL) has emerged as a promising approach for extracting valuable representations from unlabeled data. One successful SSL method is contrastive learning, which aims to bring positive examples closer…