Related papers: Unsupervised Feature Orthogonalization for Learnin…

Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…

Unpaired medical image synthesis aims to provide complementary information for an accurate clinical diagnostics, and address challenges in obtaining aligned multi-modal medical scans. Transformer-based models excel in imaging translation…

Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning. Recently, techniques for unsupervised learning of object-centric representations have raised growing interest. In…

Recently, deep learning-based models have exhibited remarkable performance for image manipulation detection. However, most of them suffer from poor universality of handcrafted or predetermined features. Meanwhile, they only focus on…

We propose a one-class neural network (OC-NN) model to detect anomalies in complex data sets. OC-NN combines the ability of deep networks to extract a progressively rich representation of data with the one-class objective of creating a…

Retrospective artifact correction (RAC) improves image quality post acquisition and enhances image usability. Recent machine learning driven techniques for RAC are predominantly based on supervised learning and therefore practical utility…

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a…

Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric…

Augmentation-based self-supervised learning methods have shown remarkable success in self-supervised visual representation learning, excelling in learning invariant features but often neglecting equivariant ones. This limitation reduces the…

Most recent view-invariant action recognition and performance assessment approaches rely on a large amount of annotated 3D skeleton data to extract view-invariant features. However, acquiring 3D skeleton data can be cumbersome, if not…

This study introduces a novel unsupervised medical image feature extraction method that employs spatial stratification techniques. An objective function based on weight is proposed to achieve the purpose of fast image recognition. The…

While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in perspective, illumination, or object deformation in the…

Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel GAN-based disentanglement framework with One-Hot Sampling and Orthogonal Regularization (OOGAN). While previous works mostly attempt to…

Hypergraph Neural Networks (HyGNNs) have demonstrated remarkable success in modeling higher-order relationships among entities. However, their performance often degrades on heterophilic hypergraphs, where nodes connected by the same…

Unsupervised learning methods for feature extraction are becoming more and more popular. We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to…

Dramatic appearance variation due to pose constitutes a great challenge in fine-grained recognition, one which recent methods using attention mechanisms or second-order statistics fail to adequately address. Modern CNNs typically lack an…

Deep networks are now ubiquitous in large-scale multi-center imaging studies. However, the direct aggregation of images across sites is contraindicated for downstream statistical and deep learning-based image analysis due to inconsistent…

In this paper, we introduce a novel task termed unified anomaly detection and classification, which aims to simultaneously detect anomalous regions in images and identify their specific categories. Existing methods typically treat anomaly…

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;…

Deep unsupervised approaches are gathering increased attention for applications such as pathology detection and segmentation in medical images since they promise to alleviate the need for large labeled datasets and are more generalizable…