arXiv subjects

Can Zhao

Publications and source records attributed to Can Zhao.

49 records · Page 3Linked to original sources

arXiv2021

DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation

Recently, neural architecture search (NAS) has been applied to automatically search high-performance networks for medical image segmentation. The NAS search space usually contains a network topology level (controlling connections among cells with different spatial scales) and a cell level (operations within each cell). Existing methods either require long searching time for large-scale 3D image datasets, or are limited to pre-defined topologies (such as U-shaped or single-path). In this work, we focus on three important aspects of NAS in 3D medical image segmentation: flexible multi-path network topology, high search efficiency, and budgeted GPU memory usage. A novel differentiable search framework is proposed to support fast gradient-based search within a highly flexible network topology search space. The discretization of the searched optimal continuous model in differentiable scheme may produce a sub-optimal final discrete model (discretization gap). Therefore, we propose a topology loss to alleviate this problem. In addition, the GPU memory usage for the searched 3D model is limited with budget constraints during search. Our Differentiable Network Topology Search scheme (DiNTS) is evaluated on the Medical Segmentation Decathlon (MSD) challenge, which contains ten challenging segmentation tasks. Our method achieves the state-of-the-art performance and the top ranking on the MSD challenge leaderboard.

cs.CV↗

arXiv2021

A Negotiation-based Right-of-way Assignment Strategy to Ensure Traffic Safety and Efficiency in Lane Change

It is widely acknowledged that verifying the safety of autonomous driving strategies requires a substantial body of simulation testing and road testing. In recent years, the formal safety methods represented by Responsibility-Sensitive Safety (RSS) have encouraged low-cost autonomous driving safety research, benefitting from its accurate assessment of safety and clear division of responsibilities. However, how to maintain traffic efficiency while ensuring safety remains a challenge. To address this problem, this paper proposes a formulized negotiation-based lane-changing strategy that makes a trade-off between safety and efficiency. Both theoretical analysis and numerical experimental results shows that compared to RSS, our strategy can noticeably improve the success rate of changing lanes on the premise of safety.

eess.SY↗

arXiv2020

LAMP: Large Deep Nets with Automated Model Parallelism for Image Segmentation

Deep Learning (DL) models are becoming larger, because the increase in model size might offer significant accuracy gain. To enable the training of large deep networks, data parallelism and model parallelism are two well-known approaches for parallel training. However, data parallelism does not help reduce memory footprint per device. In this work, we introduce Large deep 3D ConvNets with Automated Model Parallelism (LAMP) and investigate the impact of both input's and deep 3D ConvNets' size on segmentation accuracy. Through automated model parallelism, it is feasible to train large deep 3D ConvNets with a large input patch, even the whole image. Extensive experiments demonstrate that, facilitated by the automated model parallelism, the segmentation accuracy can be improved through increasing model size and input context size, and large input yields significant inference speedup compared with sliding window of small patches in the inference. Code is available\footnote{https://monai.io/research/lamp-automated-model-parallelism}.

cs.CV↗

arXiv2020

Improving the spatial resolution of a BOTDA sensor using deconvolution algorithm

Spatial resolution improvement from an acquired measurement using long pulse is developed for Brillouin optical time domain analysis (BOTDA) systems based on the total variation deconvolution algorithm. The frequency dependency of Brillouin gain temporal envelope is investigated by simulation, and its impact on the recovered results of deconvolution algorithm is thoroughly analyzed. To implement a reliable deconvolution process, differential pulse-width pair (DPP) technique is utilized to effectively eliminate the systematic BFS distortion stemming from the frequency dependency of temporal envelope. The width of the pulse pairs should be larger than 40 ns as is analyzed theoretically and verified experimentally. It has been demonstrated that the proposed method can realize flexible adjustment of spatial resolution with enhanced signal-to-noise ratio (SNR) from an established measurement with long pump pulse. In the experiment, the spatial resolution is increased to 0.5 m and 1 m with high measurement accuracy by using the deconvolution algorithm from the measurement of 60/40 ns DPP signals. Compared with the raw DPP results with the same spatial resolution, 9.2 dB and 8.4 dB SNR improvements are obtained for 0.5 m and 1 m spatial resolution respectively, thanks to the denoising capability of the total variation deconvolution algorithm. The impact of sampling rate on the recovery results is also studied. The proposed sensing system allows for distortion-free Brillouin distributed sensing with higher spatial resolution and enhanced SNR from the conventional DPP setup with long pulse pairs.

eess.SP↗

arXiv2020

Distributed Brillouin frequency shift extraction via a convolutional neural network

Distributed optical fiber Brillouin sensors detect the temperature and strain along a fiber according to the local Brillouin frequency shift, which is usually calculated by the measured Brillouin spectrum using Lorentzian curve fitting. In addition, cross-correlation, principal component analysis, and machine learning methods have been proposed for the more efficient extraction of Brillouin frequency shifts. However, existing methods only process the Brillouin spectrum individually, ignoring the correlation in the time domain, indicating that there is still room for improvement. Here, we propose and experimentally demonstrate a full convolution neural network to extract the distributed Brillouin frequency shift directly from the measured two-dimensional data. Simulated ideal Brillouin spectrum with various parameters are used to train the network. Both the simulation and experimental results show that the extraction accuracy of the network is better than that of the traditional curve fitting algorithm with a much shorter processing time. This network has good universality and robustness and can effectively improve the performances of existing Brillouin sensors.

eess.SP↗

arXiv2019

Detecting Statistically Significant Communities

Community detection is a key data analysis problem across different fields. During the past decades, numerous algorithms have been proposed to address this issue. However, most work on community detection does not address the issue of statistical significance. Although some research efforts have been made towards mining statistically significant communities, deriving an analytical solution of p-value for one community under the configuration model is still a challenging mission that remains unsolved. The configuration model is a widely used random graph model in community detection, in which the degree of each node is preserved in the generated random networks. To partially fulfill this void, we present a tight upper bound on the p-value of a single community under the configuration model, which can be used for quantifying the statistical significance of each community analytically. Meanwhile, we present a local search method to detect statistically significant communities in an iterative manner. Experimental results demonstrate that our method is comparable with the competing methods on detecting statistically significant communities.

cs.SI↗

arXiv2019

A Right-of-Way Based Strategy to Implement Safe and Efficient Driving at Non-Signalized Intersections for Automated Vehicles

Non-signalized intersection is a typical and common scenario for connected and automated vehicles (CAVs). How to balance safety and efficiency remains difficult for researchers. To improve the original Responsibility Sensitive Safety (RSS) driving strategy on the non-signalized intersection, we propose a new strategy in this paper, based on right-of-way assignment (RWA). The performances of RSS strategy, cooperative driving strategy, and RWA based strategy are tested and compared. Testing results indicate that our strategy yields better traffic efficiency than RSS strategy, but not satisfying as the cooperative driving strategy due to the limited range of communication and the lack of long-term planning. However, our new strategy requires much fewer communication costs among vehicles.

cs.RO↗

arXiv2019

Correlation-Based Community Detection

Mining community structures from the complex network is an important problem across a variety of fields. Many existing community detection methods detect communities through optimizing a community evaluation function. However, most of these functions even have high values on random graphs and may fail to detect small communities in the large-scale network (the so-called resolution limit problem). In this paper, we introduce two novel node-centric community evaluation functions by connecting correlation analysis with community detection. We will further show that the correlation analysis can provide a novel theoretical framework which unifies some existing evaluation functions in the context of a correlation-based optimization problem. In this framework, we can mitigate the resolution limit problem and eliminate the influence of random fluctuations by selecting the right correlation function. Furthermore, we introduce three key properties used in mining association rule into the context of community detection to help us choose the appropriate correlation function. Based on our introduced correlation functions, we propose a community detection algorithm called CBCD. Our proposed algorithm outperforms existing state-of-the-art algorithms on both synthetic benchmark networks and real-world networks.

cs.SI↗

arXiv2018

Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGAN

The cycleGAN is becoming an influential method in medical image synthesis. However, due to a lack of direct constraints between input and synthetic images, the cycleGAN cannot guarantee structural consistency between these two images, and such consistency is of extreme importance in medical imaging. To overcome this, we propose a structure-constrained cycleGAN for brain MR-to-CT synthesis using unpaired data that defines an extra structure-consistency loss based on the modality independent neighborhood descriptor to constrain structural consistency. Additionally, we use a position-based selection strategy for selecting training images instead of a completely random selection scheme. Experimental results on synthesizing CT images from brain MR images demonstrate that our method is better than the conventional cycleGAN and approximates the cycleGAN trained with paired data.

cs.CV↗

arXiv2018

Self Super-Resolution for Magnetic Resonance Images using Deep Networks

High resolution magnetic resonance~(MR) imaging~(MRI) is desirable in many clinical applications, however, there is a trade-off between resolution, speed of acquisition, and noise. It is common for MR images to have worse through-plane resolution~(slice thickness) than in-plane resolution. In these MRI images, high frequency information in the through-plane direction is not acquired, and cannot be resolved through interpolation. To address this issue, super-resolution methods have been developed to enhance spatial resolution. As an ill-posed problem, state-of-the-art super-resolution methods rely on the presence of external/training atlases to learn the transform from low resolution~(LR) images to high resolution~(HR) images. For several reasons, such HR atlas images are often not available for MRI sequences. This paper presents a self super-resolution~(SSR) algorithm, which does not use any external atlas images, yet can still resolve HR images only reliant on the acquired LR image. We use a blurred version of the input image to create training data for a state-of-the-art super-resolution deep network. The trained network is applied to the original input image to estimate the HR image. Our SSR result shows a significant improvement on through-plane resolution compared to competing SSR methods.

eess.IV↗

arXiv2017

Harnessing oversampling in correlation-coded OTDR

Pulse coding is an effective method to overcome the trade-off between signal-to-noise ratio (SNR) and spatial resolution in optical-fiber sensing systems based on optical time-domain reflectometry (OTDR). However, the coding gain has not been yet fully exploited. We provide a comprehensive theoretical analysis and experimental validation of the sampling criteria for correlation-coded OTDR, showing that the coding gain can be further improved by harnessing the oversampling. Moreover, the bandwidth-limited feature of the photodetector can also be utilized to select the sampling rate so that additional SNR enhancement is obtained. We believe this principle could be applied to any practical OTDR-based optical-fiber sensing technology, and serve to update existing systems based on correlation-coded OTDR in a straightforward manner at a relatively low cost.

physics.ins-det↗

arXiv2017

BOTDA using OFDM channel estimation

A novel Brillouin optical time-domain analysis (BOTDA) system is proposed using intensity-modulated optical orthogonal frequency division multiplexing probe signal and direct detection (IM-DD-OOFDM) without frequency sweep operation. The influence of peak to average power ratio (PAPR) of OFDM probe signal on the recovery of Brillouin gain spectrum (BGS) is analyzed in theory and experiment. The complex BGS is reconstructed by channel estimation algorithm and Brillouin frequency shift (BFS) is located by curve fitting of intensity spectrum. The IM-DD-OOFDM BOTDA is demonstrated experimentally with 25m spatial resolution over 2 km standard single mode fiber.

physics.ins-det↗

arXiv2014

Compact Model of Nanowire Tunneling FETs Including Phonon-Assisted Tunneling and Quantum Capacitance

A physics-based compact model for silicon gate-all-around (GAA) nanowire tunneling FETs (NW-tFETs) with good accuracy has been developed by considering Phonon-Assisted Tunneling (PAT) and transition from Quantum Capacitance Limit (QCL) to Classical Limit (CL) during the device-size scaling. The impact of PAT results in the broadening of a single electron-energy level to an energy band with density-of-states (DOS) distribution of Lorentzian shape. As a consequence, the tunneling probability at the edge of tunneling window no longer changes abruptly from zero to having a finite value. By adjusting the parameters in the Lorentzian function, an accurate fitting to the measured transfer characteristics in the subthreshold region is made possible. Besides, with an analytical formula to calculate the channel potential, the model is able to cover naturally the transition from QCL to CL regime when the device size is scaled. Furthermore, on-voltage is defined to facilitate the modeling and fitting processes. Comparisons with the experimental data demonstrate the model accuracy across all device operation regions and the flexibility in model parameter extraction is also shown.

cond-mat.mes-hall↗