Related papers: Transformer-Based Microbubble Localization
The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low recall. A common approach to address this issue is to use one-to-many label assignment to…
Place recognition is an important capability for autonomously navigating vehicles operating in complex environments and under changing conditions. It is a key component for tasks such as loop closing in SLAM or global localization. In this…
Seismic impedance inversion is one of the most important part of geophysical exploration. However, due to random noise, the traditional semi-supervised learning (SSL) methods lack generalization and stability. To solve this problem, some…
Many-body localization (MBL) in a one-dimensional Fermi Hubbard model with random on-site interactions is studied. While for this model all single-particle states are trivially delocalized, it is shown that for sufficiently strong…
In this work, we introduce OMG-Fuser, a fusion transformer-based network designed to extract information from various forensic signals to enable robust image forgery detection and localization. Our approach can operate with an arbitrary…
Beamforming is an essential step in the ultrasound image formation pipeline and has recently attracted growing interest. An important goal of beamforming is to increase the image spatial resolution, or in other words to narrow down the…
Ultrasound modulated optical tomography, also called acousto-optics tomography, is a hybrid imaging modality that aims to combine the high contrast of optical waves with the high resolution of ultrasound. We follow the model of the…
Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…
Ultrasound vascular imaging is limited by acoustic diffraction, restricting visualization of microvessels essential for understanding organ function and disease. Label-free super-resolution methods exploiting endogenous red blood cells have…
Identification of time-varying linear systems, which introduce both time-shifts (delays) and frequency-shifts (Doppler-shifts), is a central task in many engineering applications. This paper studies the problem of identification of…
Segmentation is a crucial step in microscopy image analysis. Numerous approaches have been developed over the past years, ranging from classical segmentation algorithms to advanced deep learning models. While U-Net remains one of the most…
Recent discoveries by neutrino telescopes, such as the IceCube Neutrino Observatory, relied extensively on machine learning (ML) tools to infer physical quantities from the raw photon hits detected. Neutrino telescope reconstruction…
The efficiency of beam injection in circular accelerators can be impacted by unknown aperture limitations in the vacuum chamber. These limitations can be detected by introducing localized distortions to the closed orbit of the circulating…
Recent advances in scanning transmission electron and scanning tunneling microscopies allow researchers to measure materials structural and electronic properties, such as atomic displacements and charge density modulations, at an Angstrom…
The recent detection transformer (DETR) simplifies the object detection pipeline by removing hand-crafted designs and hyperparameters as employed in conventional two-stage object detectors. However, how to leverage the simple yet effective…
Stellar astrophysics relies on diverse observational modalities-primarily photometric light curves and spectroscopic data from which fundamental stellar properties are inferred. While machine learning (ML) has advanced analysis within…
Here, we report analysis and summary of research in the field of localization microscopy for optical imaging. We introduce the basic elements of super-resolved localization microscopy methods for PALM and STORM, commonly used both in vivo…
Real-time image captioning, along with adequate precision, is the main challenge of this research field. The present work, Multiple Transformers for Self-Attention Mechanism (MTSM), utilizes multiple transformers to address these problems.…
Locating mobile devices precisely in indoor scenarios is a challenging task because of the signal diffraction and reflection in complicated environments. One vital cause deteriorating the localization performance is the inevitable power…
We introduce, design, and evaluate a set of universal receiver beamforming techniques. Our approach and system DEFORM, a Deep Learning (DL) based RX beamforming achieves significant gain for multi antenna RF receivers while being agnostic…