相关论文: A Theoretical Characterization of Optimal Data Aug…

Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Despite demonstrating comparable performance with…

Semi-Supervised Learning (SSL) has been proved to be an effective way to leverage both labeled and unlabeled data at the same time. Recent semi-supervised approaches focus on deep neural networks and have achieved promising results on…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Network intrusion detection, a well-explored cybersecurity field, has predominantly relied on supervised learning algorithms in the past two decades. However, their limitations in detecting only known anomalies prompt the exploration of…

Self-Supervised Learning (SSL) models rely on a pretext task to learn representations. Because this pretext task differs from the downstream tasks used to evaluate the performance of these models, there is an inherent misalignment or…

Self-supervised learning (SSL) has emerged as a powerful paradigm for representation learning by optimizing geometric objectives, such as invariance to augmentations, variance preservation, and feature decorrelation, without requiring…

Self-supervision is often used for pre-training to foster performance on a downstream task by constructing meaningful representations of samples. Self-supervised learning (SSL) generally involves generating different views of the same…

Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. The data representations are able to capture many underlying attributes of data, and be useful in downstream…

The core of self-supervised learning for pre-training language models includes pre-training task design as well as appropriate data augmentation. Most data augmentations in language model pre-training are context-independent. A seminal…

Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space. Contrastive learning has witnessed…

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…

Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By…

Data augmentations are important ingredients in the recipe for training robust neural networks, especially in computer vision. A fundamental question is whether neural network features encode data augmentation transformations. To answer…

Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic…

Unsupervised cross-lingual word embedding (CLWE) methods learn a linear transformation matrix that maps two monolingual embedding spaces that are separately trained with monolingual corpora. This method relies on the assumption that the two…

Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a…

Automated plant recognition plays a crucial role in biodiversity monitoring and conservation, yet current approaches rely heavily on supervised learning, which is limited by the availability of expert-labeled data. Self-supervised learning…

With the increasing utilization of deep learning in outdoor settings, its robustness needs to be enhanced to preserve accuracy in the face of distribution shifts, such as compression artifacts. Data augmentation is a widely used technique…

Contrastive learning -- a modern approach to extract useful representations from unlabeled data by training models to distinguish similar samples from dissimilar ones -- has driven significant progress in foundation models. In this work, we…