Related papers: Unsupervised Deep Contrast Enhancement with Power …

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

Dual-energy computed tomography (DECT) enables material-specific imaging through acquisitions at two different X-ray energy spectra. Material decomposition from DECT data is an ill-posed inverse problem that is highly sensitive to noise…

Self-supervised learning is an increasingly popular approach to unsupervised learning, achieving state-of-the-art results. A prevalent approach consists in contrasting data points and noise points within a classification task: this requires…

In this study, we explore the application of deep learning techniques for predicting cleansing quality in colon capsule endoscopy (CCE) images. Using a dataset of 500 images labeled by 14 clinicians on the Leighton-Rex scale (Poor, Fair,…

Event-based cameras offer reliable measurements for preforming computer vision tasks in high-dynamic range environments and during fast motion maneuvers. However, adopting deep learning in event-based vision faces the challenge of annotated…

Low noise CCDs fully-depleted up to 675 micrometers have been identified as a unique tool for Dark Matter searches and low energy neutrino physics. The charge collection efficiency (CCE) for these detectors is a critical parameter for the…

Semi-supervised segmentation methods have demonstrated promising results in natural scenarios, providing a solution to reduce dependency on manual annotation. However, these methods face significant challenges when directly applied to…

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is essential for breast cancer diagnosis due to its ability to characterize tissue through contrast agent kinetics. However, traditional DCE-MRI protocols require multiple…

Auto-Encoder based deep subspace clustering (DSC) is widely used in computer vision, motion segmentation and image processing. However, it suffers from the following three issues in the self-expressive matrix learning process: the first one…

Sub-10cm diameter nano-drones are gaining momentum thanks to their applicability in scenarios prevented to bigger flying drones, such as in narrow environments and close to humans. However, their tiny form factor also brings their major…

Low-light images, characterized by inadequate illumination, pose challenges of diminished clarity, muted colors, and reduced details. Low-light image enhancement, an essential task in computer vision, aims to rectify these issues by…

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

Deep convolutional neural networks (CNNs) for image denoising are usually trained on large datasets. These models achieve the current state of the art, but they have difficulties generalizing when applied to data that deviate from the…

The success of deep learning heavily depends on the availability of large labeled training sets. However, it is hard to get large labeled datasets in medical image domain because of the strict privacy concern and costly labeling efforts.…

We propose a new supervised dimensionality reduction technique called Supervised Linear Centroid-Encoder (SLCE), a linear counterpart of the nonlinear Centroid-Encoder (CE) \citep{ghosh2022supervised}. SLCE works by mapping the samples of a…

Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success relies on augmenting…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

Modern virtual reality headsets demand significant computational resources to render high-resolution content in real-time. Therefore, prioritizing power efficiency becomes crucial, particularly for portable versions reliant on batteries. A…

Deep learning algorithms have demonstrated state-of-the-art performance in various tasks of image restoration. This was made possible through the ability of CNNs to learn from large exemplar sets. However, the latter becomes an issue for…

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…