Related papers: Chip-level CMP Modeling and Smart Dummy for HDP an…
Crack-template-based transparent conductive films (TCFs) are promising kinds of junction-free, metallic network electrodes that can be used, e.g., for transparent electromagnetic interference (EMI) shielding. Using image processing of…
Based on deep neural networks (DNNs), deep learning has been successfully applied to many problems, but its mechanism is still not well understood -- especially the reason why over-parametrized DNNs can generalize. A recent statistical…
Multimodal structures in the sampling density (e.g. two competing phases) can be a serious problem for traditional Markov Chain Monte Carlo (MCMC), because correct sampling of the different structures can only be guaranteed for infinite…
Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and…
Diffusion models (DMs) have revolutionized image generation, producing high-quality images with applications spanning various fields. However, their ability to create hyper-realistic images poses significant challenges in distinguishing…
Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…
Efficient quality control is inevitable in the manufacturing of light-emitting diodes (LEDs). Because defective LED chips may be traced back to different causes, a time and cost-intensive electrical and optical contact measurement is…
High energy density physics (HEDP) experiments commonly involve a dynamic wave-front propagating inside a low-density foam. This effect affects its density and hence, its transparency. A common problem in foam production is the creation of…
Deep neural networks (DNNs) have achieved significant success across various tasks, but ensuring reliable uncertainty estimates, known as model calibration, is crucial for their safe and effective deployment. Modern DNNs often suffer from…
Finite elements of higher continuity, say conforming in $H^2$ instead of $H^1$, require a mapping from reference cells to mesh cells which is continuously differentiable across cell interfaces. In this article, we propose an algorithm to…
Machine-learning-based interatomic potential energy surface (PES) models are revolutionizing the field of molecular modeling. However, although much faster than electronic structure schemes, these models suffer from costly computations via…
Recent developed deep unsupervised methods allow us to jointly learn representation and cluster unlabelled data. These deep clustering methods mainly focus on the correlation among samples, e.g., selecting high precision pairs to gradually…
Atomic level qubits in silicon are attractive candidates for large-scale quantum computing, however, their quantum properties and controllability are sensitive to details such as the number of donor atoms comprising a qubit and their…
Widely used traditional pipelines for subcortical brain segmentation are often inefficient and slow, particularly when processing large datasets. Furthermore, deep learning models face challenges due to the high resolution of MRI images and…
This dissertation presents several novel deep-learning (DL)-based approaches for classifying digitally modulated signals, one method of which involves the use of capsule networks (CAPs) together with cyclic cumulant (CC) features of the…
Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs struggle to verify whether predicted concepts correspond to…
This paper reviews the recent progresses of the depth map generation for dynamic scene and its corresponding computational models. This paper mainly covers the homogeneous ambiguity models in depth sensing, resolution models in depth…
Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models.…
We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes. It is a challenging problem to estimate dense pixel correspondences between images depicting different scenes or instances of the same…
Video depth estimation is essential for providing 3D scene structure in applications ranging from autonomous driving to mixed reality. Current end-to-end video depth models have established state-of-the-art performance. Although current…