Related papers: Multi-level Asymmetric Contrastive Learning for Vo…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

Semi-supervised learning (SSL) is a promising machine learning paradigm to address the issue of label scarcity in medical imaging. SSL methods were originally developed in image classification. The state-of-the-art SSL methods in image…

Medical image representations can be learned through medical vision-language contrastive learning (mVLCL) where medical imaging reports are used as weak supervision through image-text alignment. These learned image representations can be…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly…

Current semi-supervised semantic segmentation methods mainly focus on designing pixel-level consistency and contrastive regularization. However, pixel-level regularization is sensitive to noise from pixels with incorrect predictions, and…

Semi-supervised learning addresses the issue of limited annotations in medical images effectively, but its performance is often inadequate for complex backgrounds and challenging tasks. Multi-modal fusion methods can significantly improve…

Continual learning (CL) is essential for deploying medical image segmentation models in clinical environments where imaging domains, anatomical targets, and diagnostic tasks evolve over time. However, continual segmentation still faces…

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…

In clinical practice, crossmodal information including medical images and tabular data is essential for disease diagnosis. There exists a significant modality gap between these data types, which obstructs advancements in crossmodal…

Accurate biomedical image classification under low-resource conditions remains challenging due to limited annotations, subtle inter-class visual differences, and complex disease semantics. While vision--language models offer a promising…

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank.…

Semi-supervised learning in medical image segmentation leverages unlabeled data to reduce annotation burdens through consistency learning. However, current methods struggle with class imbalance and high uncertainty from pathology…

Contrastive vision-language models such as CLIP have demonstrated strong performance across a wide range of multimodal tasks by learning from aligned image-text pairs. However, their ability to handle complex, real-world web documents…

Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) demonstrate that self-supervision is powerful to learn good representations. However, naively combining them is far from success. In this paper, we start by making the…

Contrastive learning (CL), which can extract the information shared between different contrastive views, has become a popular paradigm for vision representation learning. Inspired by the success in computer vision, recent work introduces CL…

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and…

Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-supervised learning…

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in…

Vision-language pretraining has advanced image-text alignment, yet progress in radiology remains constrained by the heterogeneity of clinical reports, including abbreviations, impression-only notes, and stylistic variability. Unlike…