arXiv subjects

Feng Gao

Publications and source records attributed to Feng Gao.

At least 253 records · Page 14Linked to original sources

arXiv2021

Deep Transformers for Fast Small Intestine Grounding in Capsule Endoscope Video

Capsule endoscopy is an evolutional technique for examining and diagnosing intractable gastrointestinal diseases. Because of the huge amount of data, analyzing capsule endoscope videos is very time-consuming and labor-intensive for gastrointestinal medicalists. The development of intelligent long video analysis algorithms for regional positioning and analysis of capsule endoscopic video is therefore essential to reduce the workload of clinicians and assist in improving the accuracy of disease diagnosis. In this paper, we propose a deep model to ground shooting range of small intestine from a capsule endoscope video which has duration of tens of hours. This is the first attempt to attack the small intestine grounding task using deep neural network method. We model the task as a 3-way classification problem, in which every video frame is categorized into esophagus/stomach, small intestine or colorectum. To explore long-range temporal dependency, a transformer module is built to fuse features of multiple neighboring frames. Based on the classification model, we devise an efficient search algorithm to efficiently locate the starting and ending shooting boundaries of the small intestine. Without searching the small intestine exhaustively in the full video, our method is implemented via iteratively separating the video segment along the direction to the target boundary in the middle. We collect 113 videos from a local hospital to validate our method. In the 5-fold cross validation, the average IoU between the small intestine segments located by our method and the ground-truths annotated by broad-certificated gastroenterologists reaches 0.945.

cs.CV↗

arXiv2021

Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks

Convolutional neural networks (CNN) have made great progress for synthetic aperture radar (SAR) images change detection. However, sampling locations of traditional convolutional kernels are fixed and cannot be changed according to the actual structure of the SAR images. Besides, objects may appear with different sizes in natural scenes, which requires the network to have stronger multi-scale representation ability. In this paper, a novel \underline{D}eformable \underline{R}esidual Convolutional Neural \underline{N}etwork (DRNet) is designed for SAR images change detection. First, the proposed DRNet introduces the deformable convolutional sampling locations, and the shape of convolutional kernel can be adaptively adjusted according to the actual structure of ground objects. To create the deformable sampling locations, 2-D offsets are calculated for each pixel according to the spatial information of the input images. Then the sampling location of pixels can adaptively reflect the spatial structure of the input images. Moreover, we proposed a novel pooling module replacing the vanilla pooling to utilize multi-scale information effectively, by constructing hierarchical residual-like connections within one pooling layer, which improve the multi-scale representation ability at a granular level. Experimental results on three real SAR datasets demonstrate the effectiveness of the proposed DRNet.

cs.CV↗

arXiv2021

Hyperspectral and LiDAR data classification based on linear self-attention

An efficient linear self-attention fusion model is proposed in this paper for the task of hyperspectral image (HSI) and LiDAR data joint classification. The proposed method is comprised of a feature extraction module, an attention module, and a fusion module. The attention module is a plug-and-play linear self-attention module that can be extensively used in any model. The proposed model has achieved the overall accuracy of 95.40\% on the Houston dataset. The experimental results demonstrate the superiority of the proposed method over other state-of-the-art models.

cs.CV↗

arXiv2021

Disentangled Non-Local Network for Hyperspectral and LiDAR Data Classification

As the ground objects become increasingly complex, the classification results obtained by single source remote sensing data can hardly meet the application requirements. In order to tackle this limitation, we propose a simple yet effective attention fusion model based on Disentangled Non-local (DNL) network for hyperspectral and LiDAR data joint classification task. In this model, according to the spectral and spatial characteristics of HSI and LiDAR, a multiscale module and a convolutional neural network (CNN) are used to capture the spectral and spatial characteristics respectively. In addition, the extracted HSI and LiDAR features are fused through some operations to obtain the feature information more in line with the real situation. Finally, the above three data are fed into different branches of the DNL module, respectively. Extensive experiments on Houston dataset show that the proposed network is superior and more effective compared to several of the most advanced baselines in HSI and LiDAR joint classification missions.

eess.IV↗

arXiv2021

Hyperspectral Image Denoising Based On Multi-Stream Denoising Network

Hyperspectral images (HSIs) have been widely applied in many fields, such as military, agriculture, and environment monitoring. Nevertheless, HSIs commonly suffer from various types of noise during acquisition. Therefore, denoising is critical for HSI analysis and applications. In this paper, we propose a novel blind denoising method for HSIs based on Multi-Stream Denoising Network (MSDNet). Our network consists of the noise estimation subnetwork and denoising subnetwork. In the noise estimation subnetwork, a multiscale fusion module is designed to capture the noise from different scales. Then, the denoising subnetwork is utilized to obtain the final denoising image. The proposed MSDNet can obtain robust noise level estimation, which is capable of improving the performance of HSI denoising. Extensive experiments on HSI dataset demonstrate that the proposed method outperforms four closely related methods.

eess.IV↗

arXiv2021

Remote Sensing Image Translation via Style-Based Recalibration Module and Improved Style Discriminator

Existing remote sensing change detection methods are heavily affected by seasonal variation. Since vegetation colors are different between winter and summer, such variations are inclined to be falsely detected as changes. In this letter, we proposed an image translation method to solve the problem. A style-based recalibration module is introduced to capture seasonal features effectively. Then, a new style discriminator is designed to improve the translation performance. The discriminator can not only produce a decision for the fake or real sample, but also return a style vector according to the channel-wise correlations. Extensive experiments are conducted on season-varying dataset. The experimental results show that the proposed method can effectively perform image translation, thereby consistently improving the season-varying image change detection performance. Our codes and data are available at https://github.com/summitgao/RSIT_SRM_ISD.

cs.CV↗

arXiv2021

Dense gas in local galaxies revealed by multiple tracers

We present 3 mm and 2 mm band simultaneously spectroscopic observations of HCN 1-0, HCO$^{+}$ 1-0, HNC 1-0, and CS 3-2 with the IRAM 30 meter telescope, toward a sample of 70 sources as nearby galaxies with infrared luminosities ranging from several 10$^{5}L_{\odot}$ to more than 10$^{12}L_{\odot}$. After combining HCN 1-0, HCO$^{+}$ 1-0 and HNC 1-0 data from literature with our detections, relations between luminosities of dense gas tracers (HCN 1-0, HCO$^{+}$ 1-0 and HNC 1-0) and infrared luminosities are derived, with tight linear correlations for all tracers. Luminosities of CS 3-2 with only our observations also show tight linear correlation with infrared luminosities. No systematic difference is found for tracing dense molecular gas among these tracers. Star formation efficiencies for dense gas with different tracers also do not show any trend along different infrared luminosities. Our study also shows that HCN/HCO$^{+}$ line ratio might not be a good indicator to diagnose obscured AGN in galaxies.

astro-ph.GA↗

arXiv2021

Experimentally Validated Hopping-Transport Model for Energetically Disordered Organic Semiconductors

Charge transport in disordered organic semiconductors occurs by hopping of charge carriers between localized sites that are randomly distributed in a strongly energy dependent density of states. Extracting disorder and hopping parameters from experimental data like temperature dependent current-voltage characteristics typically relies on parametrized mobility functionals that are integrated in a drift-diffusion solver. Surprisingly, the functional based on the extended Gaussian disorder model (eGDM) has been extremely successful at this, despite it being based on the assumption of nearest neighbor hopping (nnH) on a regular lattice. We here propose a variable range hopping (VRH) model that has been integrated in a freeware drift-diffusion solver. The mobility model has been calibrated using kinetic Monte Carlo calculations and shows good agreement with the Monte Carlo calculations over the experimentally relevant part of the parameter space. The model is applied to temperature-dependent space charge limited current (SCLC) measurements of different systems. In contrast to the eGDM, the VRH model provides a consistent description of both p-type and n-type devices. We find a critical ratio of aNN/$α$ (mean inter-site distance / localization radius) of ~3 below which hopping to non-nearest neighbors becomes important around room temperature and the eGDM cannot be used for parameter extraction. Typical (Gaussian) disorder values in the range 45-120 meV are found, without any clear correlation with photovoltaic performance when the same active layer is used in an organic solar cell.

cond-mat.mtrl-sci↗

arXiv2021

Short Text Classification via Knowledge powered Attention with Similarity Matrix based CNN

Short text is becoming more and more popular on the web, such as Chat Message, SMS and Product Reviews. Accurately classifying short text is an important and challenging task. A number of studies have difficulties in addressing this problem because of the word ambiguity and data sparsity. To address this issue, we propose a knowledge powered attention with similarity matrix based convolutional neural network (KASM) model, which can compute comprehensive information by utilizing the knowledge and deep neural network. We use knowledge graph (KG) to enrich the semantic representation of short text, specially, the information of parent-entity is introduced in our model. Meanwhile, we consider the word interaction in the literal-level between short text and the representation of label, and utilize similarity matrix based convolutional neural network (CNN) to extract it. For the purpose of measuring the importance of knowledge, we introduce the attention mechanisms to choose the important information. Experimental results on five standard datasets show that our model significantly outperforms state-of-the-art methods.

cs.CL↗

arXiv2021

Fast Outage Analysis of Large-scale Production Clouds with Service Correlation Mining

Cloud-based services are surging into popularity in recent years. However, outages, i.e., severe incidents that always impact multiple services, can dramatically affect user experience and incur severe economic losses. Locating the root-cause service, i.e., the service that contains the root cause of the outage, is a crucial step to mitigate the impact of the outage. In current industrial practice, this is generally performed in a bootstrap manner and largely depends on human efforts: the service that directly causes the outage is identified first, and the suspected root cause is traced back manually from service to service during diagnosis until the actual root cause is found. Unfortunately, production cloud systems typically contain a large number of interdependent services. Such a manual root cause analysis is often time-consuming and labor-intensive. In this work, we propose COT, the first outage triage approach that considers the global view of service correlations. COT mines the correlations among services from outage diagnosis data. After learning from historical outages, COT can infer the root cause of emerging ones accurately. We implement COT and evaluate it on a real-world dataset containing one year of data collected from Microsoft Azure, one of the representative cloud computing platforms in the world. Our experimental results show that COT can reach a triage accuracy of 82.1%~83.5%, which outperforms the state-of-the-art triage approach by 28.0%~29.7%.

cs.SE↗

arXiv2021

Acoustic radiation-free surface phononic crystal resonator for in-liquid low-noise gravimetric detection

Acoustic wave resonators are promising for gravimetric biosensing. However, they generally suffer from strong acoustic radiation in liquid, which limits their quality factor and increases their frequency noise. This article presents an acoustic-radiation-free gravimetric biosensor based on a locally-resonant surface phononic crystal (SPC) consisting of periodic high aspect ratio electrodes to ad-dress the above issue. The acoustic wave generated in the SPC is slower than the sound wave in water, hence preventing acoustic propagation in the fluid and resulting in energy confinement near the electrode surface. This energy confinement results in a significant quality factor improvement and thus reduces the frequency noise. The proposed SPC resonator is numerically studied by finite element analysis and experimentally implemented by an electroplating based fabrication process. Experimental results show that the SPC resonator exhibits an in-liquid quality factor 15 times higher than a conventional Rayleigh wave resonator with a similar operating frequency. The proposed radiation suppression method using SPC can also be applied in other types of acoustic wave resonators. It can thus serve as a general technique for boosting the in-liquid quality factor and the sensing performance of many acoustic biosensors.

physics.app-ph↗

arXiv2021

The dynamic energy balance in earthquakes expressed by fault surface morphology

The dynamic energy balance is essential for earthquake studies. The energy balance approach is one of the most famous developments in fracture mechanics. To interpret seismological data, crack models and sliding on a frictional surface (fault) models are widely used. The macroscopically observable energy budget and the microscopic processes can be related through the fracture energy $G_c$. The fault surface morphology is the direct result of the microscopic processes near the crack tip or on the frictional interface. Here we show that the dynamic energy balance in earthquakes can be expressed by fault surface morphology, and that they are quantitatively linked. The direct shear experiments proves the predictions of the theoretical discussions, and show that the strain rate has crucial influence on the dynamic energy balance.

physics.geo-ph↗

arXiv2020

Nonlinear effects in locally-resonant nanostrip phononic metasurface at GHz frequencies

In this paper, we report on the observation of nonlinear effects in a nanostrip phononic metasurface (NPM) that enable the tuning of resonance frequencies at 1.42 GHz. The NPM resonator made of periodic nanostrip array is fabricated on a lithium niobate substrate. Each of the nanostrip is 250-nm wide and is made of 680-nm-thick SiO2 layer stacking on 50-nm Al metal electrodes. Finite element analysis reveals that the device operates in a vertically polarized (compression) mode with substantial acoustic energy confined in the nanostrips, leading to a local resonance at low acoustic velocity. Due to the nonlinearity, the resonance frequency of the device decreases quadratically with the increase of stimulation power from 10 to 30 dBm. The underlying mechanism of the nonlinearity is found to be the power-dependent coupling of the adjacent nanostrips. This coupling induces softening of the substrate surface region, which reduces the acoustic velocity and hence the bulk radiation. As a result, the quality factor of the NPM resonator is found to improve with the increase of stimulation power. The power-dependent coupling of nanostrips in the NPM resonator demonstrates a reliable method for the realization of nonlinearity in phononic metasurfaces, which would significantly enrich the mechanisms for the manipulation of surface acoustic waves at high frequencies.

physics.app-ph↗

arXiv2020

Superposed Wave (s-Wave): Accelerating Photoacoustic Simulation

Photoacoustic imaging develops very fast in recent years due to its superior performance in many preclinical and clinical applications. However, it is still in a developing stage, and a lot of experiments have to be performed in a simulation setting. To simulate photoacoustic imaging in a computer, k-Wave is currently the most popular MATLAB toolbox. Lots of research groups choose k-Wave toolbox to perform the forward projection process, which also can be described as forward model. However, by solving complex partial differential equation, k-Wave suffers a lot from computation time. To accelerate photoacoustic simulation, in this paper, we propose a straightforward simulation approach based on superposed Wave (s-Wave). Specifically, we treat the initial pressure distribution as a set of single pixels. Then by pre-obtaining a standard sensor data from single pixel, we can easily use loop and multiplication operators to change phase and amplitude of sensor data for given pixels. We use three different 2D samples and two 3D samples to test the time cost. The result of our proposed s-Wave method shows much less time consumption compared with k-wave. Especially in a sparse configuration in 3D, s-Wave is more than 2000 times faster than k-Wave, whiling getting nearly same sensor data.

physics.med-ph↗

arXiv2020

Time-reversed photoacoustic guided time-reversed ultrasonically encoded optical focusing

Deep-tissue optical imaging is a longstanding challenge limited by scattering. Both optical imaging and treatment can benefit from focusing light in deep tissue beyond one transport mean free path. Wavefront shaping based on time-reversed ultrasonically encoded (TRUE) optical focusing utilizes ultrasound focus, which is much less scattered than light in biological tissues as the 'guide star'. However, the traditional TRUE is limited by the ultrasound focusing area and pressure tagging efficiency, especially in acoustically heterogeneous medium. Even the improved version of iterative TRUE comes at a large time consumption, which limits the application of TRUE. To address this problem, we proposed a method called time-reversed photoacoustic wave guided time-reversed ultrasonically encoded (TRPA-TRUE) optical focusing by integrating ultrasonic focus guided by time-reversing PA signals, and the ultrasound modulation of diffused coherent light with optical phase conjugation (OPC), achieving dynamic focusing of light into scattering medium. Simulation results show that the focusing accuracy of the proposed method has been significantly improved compared with conventional TRUE, which is more suitable for practical applications that suffers severe acoustic distortion, e.g. transcranial optical focusing.

physics.optics↗

arXiv2020

Low-Cost Optoacoustic Tomography System with Programmable Acoustic Delay-Line

Photoacoustic tomography (PAT) is an emerging technology for biomedical imaging that combines the superiorities of high optical contrast and acoustic penetration. In the PAT system, more photoacoustic (PA) signals are preferred to be detected from full field of view to reconstruct PA images with higher fidelity. However, the requirement for more PA signals detection leads to more time consumption for single-channel scanning based PAT system, or higher cost of data acquisition (DAQ) module for an array-based PAT system. To address this issue, we proposed a programmable acoustic delay line module to reduce DAQ cost and accelerate imaging speed for PAT system. The module is based on bidirectional conversion between acoustic signals and electrical signals, including ultrasound transmission in between to provide sufficient time delay. The acoustic delay line module achieves tens or hundreds of microseconds delay for each channel, and is controlled by a programmable control unit. In this work, it achieves to merge four inputs of PA signals into one output signal, which can be recovered into original four PA signals in the digital domain after DAQ. The imaging experiments of pencil leads embedded in agar phantom is conducted by the PAT system equipped with the proposed programmable acoustic delay-line module, which demonstrated its feasibility in biomedical imaging system.

physics.ins-det↗

arXiv2020

Deep learning for photoacoustic imaging: a survey

Machine learning has been developed dramatically and witnessed a lot of applications in various fields over the past few years. This boom originated in 2009, when a new model emerged, that is, the deep artificial neural network, which began to surpass other established mature models on some important benchmarks. Later, it was widely used in academia and industry. Ranging from image analysis to natural language processing, it fully exerted its magic and now become the state-of-the-art machine learning models. Deep neural networks have great potential in medical imaging technology, medical data analysis, medical diagnosis and other healthcare issues, and is promoted in both pre-clinical and even clinical stages. In this review, we performed an overview of some new developments and challenges in the application of machine learning to medical image analysis, with a special focus on deep learning in photoacoustic imaging. The aim of this review is threefold: (i) introducing deep learning with some important basics, (ii) reviewing recent works that apply deep learning in the entire ecological chain of photoacoustic imaging, from image reconstruction to disease diagnosis, (iii) providing some open source materials and other resources for researchers interested in applying deep learning to photoacoustic imaging.

cs.CV↗

arXiv2020

Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes

Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots. However, the rigid projection computed by ego-motion cannot represent all scene points, such as points on moving objects, leading to false guidance in these regions. To address this problem, we propose an Attentional Separation-and-Aggregation Network (ASANet), which can learn to distinguish and extract the scene's static and dynamic characteristics via the attention mechanism. We further propose a novel MotionNet with an ASANet as the encoder, followed by two separate decoders, to estimate the camera's ego-motion and the scene's dynamic motion field. Then, we introduce an auto-selecting approach to detect the moving objects for dynamic-aware learning automatically. Empirical experiments demonstrate that our method can achieve the state-of-the-art performance on the KITTI benchmark.

cs.CV↗