Related papers: Benchmarking Vision-Language Contrastive Methods f…

This work studies the relationship between Contrastive Learning and Domain Adaptation from a theoretical perspective. The two standard contrastive losses, NT-Xent loss (Self-supervised) and Supervised Contrastive loss, are related to the…

Recent advancements in machine learning (ML), natural language processing (NLP), and foundational models have shown promise for real-life applications in critical, albeit compute-constrainted fields like healthcare. In such areas, combining…

Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge for medical imaging data. While pre-trained deep networks on ImageNet and vision-language foundation models…

Multi-modal medical imaging enables comprehensive diagnostics, yet current foundation models process 2D (e.g. X-ray) and 3D (e.g. CT) data with separate, dimensionality-specific architectures. We present MultiMedVision, a unified framework…

Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels. This paper introduces a self-supervised learning…

During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification…

This paper investigates the critical problem of representation similarity evolution during cross-domain transfer learning, with particular focus on understanding why pre-trained models maintain effectiveness when adapted to medical imaging…

Medical Visual Question Answering (Medical-VQA) aims to to answer clinical questions regarding radiology images, assisting doctors with decision-making options. Nevertheless, current Medical-VQA models learn cross-modal representations…

The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…

This paper presents a novel positive and negative set selection strategy for contrastive learning of medical images based on labels that can be extracted from clinical data. In the medical field, there exists a variety of labels for data…

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings…

Multi-modal medical image segmentation plays an essential role in clinical diagnosis. It remains challenging as the input modalities are often not well-aligned spatially. Existing learning-based methods mainly consider sharing trainable…

The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing high quality representations could be of great value. It is…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…

Unpaired image-to-image translation aims to find a mapping between the source domain and the target domain. To alleviate the problem of the lack of supervised labels for the source images, cycle-consistency based methods have been proposed…

Contrastive learning has made considerable progress in computer vision, outperforming supervised pretraining on a range of downstream datasets. However, is contrastive learning the better choice in all situations? We demonstrate two cases…

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…

Self-supervised deep learning has accelerated 2D natural image analysis but remains difficult to translate into 3D MRI, where data are scarce and pre-trained 2D backbones cannot capture volumetric context. We present a…

Contrastive learning has proven effective for pre-training image models on unlabeled data with promising results for tasks such as medical image classification. Using paired text (like radiological reports) during pre-training improves the…

Classical machine learners are designed only to tackle one task without capability of adopting new emerging tasks or classes whereas such capacity is more practical and human-like in the real world. To address this shortcoming, continual…