相关论文: Surrogate- and invariance-boosted contrastive lear…

Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e.g., radiological scores). Access to high-confidence labels, such as histology-based diagnoses, is rare and costly. Pretraining…

Semi-supervised learning utilizes insights from unlabeled data to improve model generalization, thereby reducing reliance on large labeled datasets. Most existing studies focus on limited samples and fail to capture the overall data…

Multi-label classification, which involves assigning multiple labels to a single input, has emerged as a key area in both research and industry due to its wide-ranging applications. Designing effective loss functions is crucial for…

Deep learning has revolutionized medical imaging, but its effectiveness is severely limited by insufficient labeled training data. This paper introduces a novel GAN-based semi-supervised learning framework specifically designed for low…

Deep learning models are modern tools for spatio-temporal graph (STG) forecasting. Though successful, we argue that data scarcity is a key factor limiting their recent improvements. Meanwhile, contrastive learning has been an effective…

Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…

Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the…

Improving generalization is a major challenge in audio classification due to labeled data scarcity. Self-supervised learning (SSL) methods tackle this by leveraging unlabeled data to learn useful features for downstream classification…

The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the…

Datasets for biosignals, such as electroencephalogram (EEG) and electrocardiogram (ECG), often have noisy labels and have limited number of subjects (<100). To handle these challenges, we propose a self-supervised approach based on…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

Deep neural networks perform remarkably well in close-world scenarios. However, novel classes emerged continually in real applications, making it necessary to learn incrementally. Class-incremental learning (CIL) aims to gradually recognize…

Learning time-series representations when only unlabeled data or few labeled samples are available can be a challenging task. Recently, contrastive self-supervised learning has shown great improvement in extracting useful representations…

Self-supervised learning has achieved a great success in the representation learning of visual and textual data. However, the current methods are mainly validated on the well-curated datasets, which do not exhibit the real-world long-tailed…

After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy. Contrastive learning has demonstrated its great potential in learning from unlabeled data. However,…

Self-supervised contrastive learning is a powerful tool to learn visual representation without labels. Prior work has primarily focused on evaluating the recognition accuracy of various pre-training algorithms, but has overlooked other…

Large amounts of labeled data are typically required to train deep learning models. For many real-world problems, however, acquiring additional data can be expensive or even impossible. We present semi-supervised deep kernel learning…

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…

Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains. The success of constrastive learning in single-label classifications motivates us to…

Supervised learning can improve the design of state-of-the-art solvers for combinatorial problems, but labelling large numbers of combinatorial instances is often impractical due to exponential worst-case complexity. Inspired by the recent…