Related papers: CCRL: Contrastive Cell Representation Learning

Artificial intelligence (AI) is anticipated to play a pivotal role in 6G. However, a key challenge in developing AI-powered solutions is the extensive data collection and labeling efforts required to train supervised deep learning models.…

Unsupervised (a.k.a. Self-supervised) representation learning (URL) has emerged as a new paradigm for time series analysis, because it has the ability to learn generalizable time series representation beneficial for many downstream tasks…

Contrastive learning has been frequently investigated to learn effective representations for text clustering tasks. While existing contrastive learning-based text clustering methods only focus on modeling instance-wise semantic similarity…

The objective of this paper is to learn semantic representations for sleep stage classification from raw physiological time series. Although supervised methods have gained remarkable performance, they are limited in clinical situations due…

Graph representation learning (GRL) has emerged as a powerful technique for solving graph analytics tasks. It can effectively convert discrete graph data into a low-dimensional space where the graph structural information and graph…

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the…

Effective protein representation learning is crucial for predicting protein functions. Traditional methods often pretrain protein language models on large, unlabeled amino acid sequences, followed by finetuning on labeled data. While…

Computed tomography (CT) samples with pathological annotations are difficult to obtain. As a result, the computer-aided diagnosis (CAD) algorithms are trained on small datasets (e.g., LIDC-IDRI with 1,018 samples), limiting their accuracies…

Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…

State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost compared to conventional CNN models. Striving to maximize the mutual information of two…

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear what characteristics of their representations lead to high downstream accuracies. In this work, we characterize properties that SSL representations…

This paper proposes an efficient system for classifying cervical cancer cells using pre-trained convolutional neural networks (CNNs). We first fine-tune five pre-trained CNNs and minimize the overall cost of misclassification by…

Early cancer detection is crucial for prognosis, but many cancer types lack large labelled datasets required for developing deep learning models. This paper investigates self-supervised learning (SSL) as an alternative to the standard…

Attempting to fully exploit the rich information of topological structure and node features for attributed graph, we introduce self-supervised learning mechanism to graph representation learning and propose a novel Self-supervised Consensus…

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality…

Self-supervised learning (SSL) on graphs generates node and graph representations (i.e., embeddings) that can be used for downstream tasks such as node classification, node clustering, and link prediction. Graph SSL is particularly useful…

Self-supervised learning (SSL) has proven to be a powerful approach for extracting biologically meaningful representations from single-cell data. To advance our understanding of SSL methods applied to single-cell data, we present…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

Part feature learning is critical for fine-grained semantic understanding in vehicle re-identification. However, existing approaches directly model part features and global features, which can easily lead to serious gradient vanishing…

Over the last decade, supervised deep learning on manually annotated big data has been progressing significantly on computer vision tasks. But the application of deep learning in medical image analysis was limited by the scarcity of…