Simiao Ren
YOU?
Author Swipe
View article: Automated irregularity characterization and restoration prioritization for stone masonry heritage structures using image processing and deep learning
Automated irregularity characterization and restoration prioritization for stone masonry heritage structures using image processing and deep learning Open
View article: Do Deepfake Detectors Work in Reality?
Do Deepfake Detectors Work in Reality? Open
View article: SODU2-NET: a novel deep learning-based approach for salient object detection utilizing U-NET
SODU2-NET: a novel deep learning-based approach for salient object detection utilizing U-NET Open
Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. To address this challenge posed by complex backgrounds in salient object detectio…
View article: The Exploration of the Semantic Expansion Path and Generality Motivation of “Rock/Burn” Based on Image Schema
The Exploration of the Semantic Expansion Path and Generality Motivation of “Rock/Burn” Based on Image Schema Open
Catchwords have enriched the language during its development. In recent years, in addition to the basic original meaning of “rock/burn”, some new usages such as “too rocking” and “let us rock” have appeared in the network language. The pol…
View article: Can AI Assist in Olympiad Coding
Can AI Assist in Olympiad Coding Open
As artificial intelligence programs have become more powerful, their capacity for problem-solving continues to increase, approaching top-level competitors in many olympiads. Continued development of models and benchmarks is important but n…
View article: Deep Learning Resolves Myovascular Dynamics in the Failing Human Heart
Deep Learning Resolves Myovascular Dynamics in the Failing Human Heart Open
The adult mammalian heart harbors minute levels of cycling cardiomyocytes (CMs). Large numbers of images are needed to accurately quantify cycling events using microscopy-based methods. CardioCount is a new deep learning-based pipeline to …
View article: Transfer learning for metamaterial design and simulation
Transfer learning for metamaterial design and simulation Open
We demonstrate transfer learning as a tool to improve the efficacy of training deep learning models based on residual neural networks (ResNets). Specifically, we examine its use for study of multi-scale electrically large metasurface array…
View article: Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling
Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling Open
We propose and show the efficacy of a new method to address generic inverse problems. Inverse modeling is the task whereby one seeks to determine the hidden parameters of a natural system that produce a given set of observed measurements. …
View article: Machine Learning for Mie-Tronics
Machine Learning for Mie-Tronics Open
Electromagnetic multipole expansion theory underpins nanoscale light-matter interactions, particularly within subwavelength meta-atoms, paving the way for diverse and captivating optical phenomena. While conventionally brute force optimiza…
View article: Segment anything, from space?
Segment anything, from space? Open
Recently, the first foundation model developed specifically for image segmentation tasks was developed, termed the "Segment Anything Model" (SAM). SAM can segment objects in input imagery based on cheap input prompts, such as one (or more)…
View article: Does Deep Active Learning Work in the Wild?
Does Deep Active Learning Work in the Wild? Open
Deep active learning (DAL) methods have shown significant improvements in sample efficiency compared to simple random sampling. While these studies are valuable, they nearly always assume that optimal DAL hyperparameter (HP) settings are k…
View article: Deep Learning Resolves Myovascular Dynamics in the Failing Human Heart
Deep Learning Resolves Myovascular Dynamics in the Failing Human Heart Open
View article: Closing the domain gap: blended synthetic imagery for climate object detection
Closing the domain gap: blended synthetic imagery for climate object detection Open
Accurate geospatial information about the causes and consequences of climate change, including energy systems infrastructure, is critical to planning climate change mitigation and adaptation strategies. When up-to-date spatial data on infr…
View article: Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling
Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling Open
We propose and show the efficacy of a new method to address generic inverse problems. Inverse modeling is the task whereby one seeks to determine the control parameters of a natural system that produce a given set of observed measurements.…
View article: Self-Supervised Encoders Are Better Transfer Learners in Remote Sensing Applications
Self-Supervised Encoders Are Better Transfer Learners in Remote Sensing Applications Open
Transfer learning has been shown to be an effective method for achieving high-performance models when applying deep learning to remote sensing data. Recent research has demonstrated that representations learned through self-supervision tra…
View article: Heterogeneity and Memory Effect in the Sluggish Dynamics of Vacancy Defects in Colloidal Disordered Crystals and Their Implications to High‐Entropy Alloys
Heterogeneity and Memory Effect in the Sluggish Dynamics of Vacancy Defects in Colloidal Disordered Crystals and Their Implications to High‐Entropy Alloys Open
Vacancy dynamics of high‐density 2D colloidal crystals with a polydispersity in particle size are studied experimentally. Heterogeneity in vacancy dynamics is observed. Inert vacancies that hardly hop to other lattice sites and active vaca…
View article: Deep inverse photonic design: A tutorial
Deep inverse photonic design: A tutorial Open
View article: Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis
Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis Open
View article: Utilizing Geospatial Data for Assessing Energy Security: Mapping Small Solar Home Systems Using Unmanned Aerial Vehicles and Deep Learning
Utilizing Geospatial Data for Assessing Energy Security: Mapping Small Solar Home Systems Using Unmanned Aerial Vehicles and Deep Learning Open
Solar home systems (SHS), a cost-effective solution for rural communities far from the grid in developing countries, are small solar panels and associated equipment that provides power to a single household. A crucial resource for targetin…
View article: Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis
Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis Open
High quality energy systems information is a crucial input to energy systems research, modeling, and decision-making. Unfortunately, actionable information about energy systems is often of limited availability, incomplete, or only accessib…
View article: Towards Robust Deep Active Learning for Scientific Computing
Towards Robust Deep Active Learning for Scientific Computing Open
Deep learning (DL) is revolutionizing the scientific computing community. To reduce the data gap, active learning has been identified as a promising solution for DL in the scientific computing community. However, the deep active learning (…
View article: Utilizing geospatial data for assessing energy security: Mapping small solar home systems using unmanned aerial vehicles and deep learning
Utilizing geospatial data for assessing energy security: Mapping small solar home systems using unmanned aerial vehicles and deep learning Open
Solar home systems (SHS), a cost-effective solution for rural communities far from the grid in developing countries, are small solar panels and associated equipment that provides power to a single household. A crucial resource for targetin…
View article: Deep Inverse Photonic Design: A Tutorial
Deep Inverse Photonic Design: A Tutorial Open
View article: Inverse deep learning methods and benchmarks for artificial electromagnetic material design
Inverse deep learning methods and benchmarks for artificial electromagnetic material design Open
Solving inverse material design problems with deep learning: we compare eight deep learning models on three problems, identifying the best approaches and demonstrating that they are highly effective.
View article: UAV-based solar photovoltaic detection dataset
UAV-based solar photovoltaic detection dataset Open
This dataset contains unmanned aerial vehicle (UAV) imagery (a.k.a. drone imagery) and annotations of solar panel locations captured from controlled flights at various altitudes and speeds across two sites at Duke Forest (Couch field and B…
View article: Solar photovoltaic annotations for computer vision related to the "Classification Training Dataset for Crop Types in Rwanda" drone imagery dataset
Solar photovoltaic annotations for computer vision related to the "Classification Training Dataset for Crop Types in Rwanda" drone imagery dataset Open
This dataset contains annotations (i.e. polygons) for solar photovoltaic (PV) objects in the previously published dataset "Classification Training Dataset for Crop Types in Rwanda" published by RTI International (DOI: 10.34911/rdnt.r4p1fr …
View article: Dataset: ADM neural simulator for "Inverse deep learning methods and benchmarks for artificial electromagnetic material design"
Dataset: ADM neural simulator for "Inverse deep learning methods and benchmarks for artificial electromagnetic material design" Open
The neural simulator for the ADM dataset of "Inverse deep learning methods and benchmarks for artificial electromagnetic material design"For the usage, please refer to github page: https://github.com/BensonRen/AEM_DIM_BenchNote that this i…
View article: Inverse deep learning methods and benchmarks for artificial electromagnetic material design
Inverse deep learning methods and benchmarks for artificial electromagnetic material design Open
Deep learning (DL) inverse techniques have increased the speed of artificial electromagnetic material (AEM) design and improved the quality of resulting devices. Many DL inverse techniques have succeeded on a number of AEM design tasks, bu…
View article: Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions
Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions Open
Numerous physical systems are described by ordinary or partial differential equations whose solutions are given by holomorphic or meromorphic functions in the complex domain. In many cases, only the magnitude of these functions are observe…
View article: Data from: Benchmarking deep learning architectures for artificial electromagnetic material problems
Data from: Benchmarking deep learning architectures for artificial electromagnetic material problems Open
Artificial electromagnetic materials (AEMs), including metamaterials, derive their electromagnetic properties from geometry rather than chemistry. With the appropriate geometric design, AEMs have achieved exotic properties not realizable w…