相关论文: Contrastive Cross-Modal Pre-Training: A General St…

Deep neural networks are increasingly used in medical imaging for tasks such as pathological classification, but they face challenges due to the scarcity of high-quality, expert-labeled training data. Recent efforts have utilized…

Recently, the cross-modal pretraining model has been employed to produce meaningful pseudo-labels to supervise the training of an image clustering model. However, numerous erroneous alignments in a cross-modal pre-training model could…

Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. It has recently emerged as one of the leading learning paradigms in the absence of labels…

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…

Image captioning models require the high-level generalization ability to describe the contents of various images in words. Most existing approaches treat the image-caption pairs equally in their training without considering the differences…

Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences…

Traditional supervised learning with deep neural networks requires a tremendous amount of labelled data to converge to a good solution. For 3D medical images, it is often impractical to build a large homogeneous annotated dataset for a…

Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and…

Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to…

Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a…

Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data. However, most existing approaches do not explicitly capture high-level semantic relations between distant…

Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation process lags down the speed of further advances.…

Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations. The idea is to make features of transformed versions of the same images similar…

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…

Current supervised cross-domain image retrieval methods can achieve excellent performance. However, the cost of data collection and labeling imposes an intractable barrier to practical deployment in real applications. In this paper, we…

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…

This paper is concerned with contrastive learning (CL) for low-level image restoration and enhancement tasks. We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an…

Deep learning in medical imaging has the potential to minimize the risk of diagnostic errors, reduce radiologist workload, and accelerate diagnosis. Training such deep learning models requires large and accurate datasets, with annotations…

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…

Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-level features that humans deem non-semantic. This dependency…