Measuring animal behaviors is a crucial task in a range of scientific applications. Modern approaches with deep neural networks calls for developing solutions that solve a wide range of vision and language tasks. This ubiquitous need for understanding beha ...
Microscopy is one of the essential tools to quantify and advance our understanding of living systems. Modern digital microscopes enable measurements at unprecedented spatiotemporal scale, so automated processing methods are required to complete tasks such ...
The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...
In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...
This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...
In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...
We formulate an optimization problem to estimate probability densities in the context of multidimensional problems that are sampled with uneven probability. It considers detector sensitivity as an heterogeneous density and takes advantage of the computatio ...
Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...
In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...
Quantum ghost imaging can be an important tool in making optical measurements. One of the most useful aspects of ghost imaging is the unique ability to correlate two sets of independently collected information. We aim to use the principles of ghost imaging ...
The acquisition of the time of flight (ToF) of photons has found numerous applications in the biomedical field. Over the last decades, a few strategies have been proposed to deconvolve the temporal instrument response function (IRF) that distorts the exper ...
Fundamental properties of light unavoidably impose features on images collected using fluorescence microscopes. Accounting for these features is often critical in quantitatively interpreting microscopy images, especially those gathering information at scal ...
Advancing quantum technologies depends on the precise control of individual quantum systems, the so-called qubits, and the exploitation of their quantum properties. Nowadays, expanding the number of qubits to be entangled is at the core of the developments ...
In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches have shown remarkable success on synthetic datasets, we have observed them to fail in the presence of real-world data. We ...
Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...
The invention of 3D atomic force microscopy (3D-AFM) has enabled visualizing subnanoscale 3D hydration structures. Meanwhile, its applications to imaging flexible molecular chains have started to be experimentally explored. However, the validity and princi ...
In recent years, exploring deep generative models for generating time series has garnered significant interest within the research community. These models have found wide-ranging applications in areas such as data augmentation, scenario simulation, and the ...
Institute of Electrical and Electronics Engineers Inc.2024
After decades of technological advancements, high-speed atomic force microscopy (HS-AFM) has emerged as a powerful technique for visualizing dynamic processes. At the nanoscale, the AFM provides valuable insights into the sample by sensing minute interacti ...
Situational awareness strategies are essential for the reliable and secure operation of the electric power grid which represents critical infrastructure in modern society. With the rise of converter-interfaced renewable generation and the consequent shift ...
The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preservi ...
