Related papers: ISImed: A Framework for Self-Supervised Learning u…

We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local…

Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to…

The scarcity of labeled data often impedes the application of deep learning to the segmentation of medical images. Semi-supervised learning seeks to overcome this limitation by exploiting unlabeled examples in the learning process. In this…

Low-shot learning indicates the ability to recognize unseen objects based on very limited labeled training samples, which simulates human visual intelligence. According to this concept, we propose a multi-level similarity model (MLSM) to…

Federated learning (FL) has emerged with increasing popularity to collaborate distributed medical institutions for training deep networks. However, despite existing FL algorithms only allow the supervised training setting, most hospitals in…

Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices…

The success of deep learning has been witnessed as a promising technique for computer-aided biomedical image analysis, due to end-to-end learning framework and availability of large-scale labelled samples. However, in many cases of…

This paper introduces self-supervised neural network models to tackle several fundamental problems in the field of 3D human body analysis and processing. First, we propose VariShaPE (Varifold Shape Parameter Estimator), a novel architecture…

Self-supervised learning (SSL) is attractive for plant disease detection as it can exploit large collections of unlabeled leaf images, yet most existing SSL methods are built on CNNs or vision transformers that are poorly matched to…

This paper introduces a novel approach to improving the training stability of self-supervised learning (SSL) methods by leveraging a non-parametric memory of seen concepts. The proposed method involves augmenting a neural network with a…

We propose a novel deep-learning framework for super-resolution ultrasound images and videos in terms of spatial resolution and line reconstruction. We up-sample the acquired low-resolution image through a vision-based interpolation method;…

Self-supervised, multi-modal learning has been successful in holistic representation of complex scenarios. This can be useful to consolidate information from multiple modalities which have multiple, versatile uses. Its application in…

At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…

Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have long-tailed label distributions, where we know little…

The necessity of large amounts of labeled data to train deep models, especially in medical imaging creates an implementation bottleneck in resource-constrained settings. In Insite (labelINg medical imageS usIng submodular funcTions and…

Supervised deep learning-based methods yield accurate results for medical image segmentation. However, they require large labeled datasets for this, and obtaining them is a laborious task that requires clinical expertise.…

State-of-the-art machine learning models, and especially deep learning ones, are significantly data-hungry; they require vast amounts of manually labeled samples to function correctly. However, in most medical imaging fields, obtaining said…

Self-supervised learning has been known for learning good representations from data without the need for annotated labels. We explore the simple siamese (SimSiam) architecture for representation learning on strong gravitational lens images.…

Self-supervised learning has witnessed great progress in vision and NLP; recently, it also attracted much attention to various medical imaging modalities such as X-ray, CT, and MRI. Existing methods mostly focus on building new pretext…

High-resolution medical images are beneficial for analysis but their acquisition may not always be feasible. Alternatively, high-resolution images can be created from low-resolution acquisitions using conventional upsampling methods, but…