Matching Network Research Articles

Channel-Aware Decoupling Network for Multiturn Dialog Comprehension.

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pretrained language models (PrLMs). In contrast to the plain-text modeling as the focus of the PrLMs, dialog texts involve multiple speakers and reflect special characteristics, such as topic transitions and structure dependencies, between distant utterances. However, the related PrLM models commonly represent dialogs sequentially by processing the pairwise dialog history as a whole. Thus, the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose compositional learning for holistic interaction across the utterances beyond the sequential contextualization from PrLMs, in order to capture the utterance-aware and speaker-aware representations entailed in a dialog history. We decouple the contextualized word representations by masking mechanisms in transformer-based PrLM, making each word only focus on the words in the current utterance, other utterances, and two speaker roles (i.e., utterances of the sender and utterances of the receiver), respectively. In addition, we employ domain-adaptive training strategies to help the model adapt to the dialog domains. Experimental results show that our method substantially boosts the strong PrLM baselines in four public benchmark datasets, achieving new state-of-the-art performance over previous methods.

A cascaded GRU-based stereoscopic matching network for precise plank measurement

Wooden plank images in industrial measurements often contain numerous textureless areas. Furthermore, due to the thin plate structure, the three-dimensional (3D) disparity of these planks is predominantly confined to a narrow range. Consequently, achieving accurate 3D matching of wooden plank images has consistently presented a challenging task within the industry. In recent years, deep learning has progressively supplanted traditional stereo matching methods due to its inherent advantages, including rapid inference and end-to-end processing. Nonetheless, the acquisition of datasets for stereo matching networks poses an additional challenge, primarily attributable to the difficulty in obtaining accurate disparity data. Thus, this paper presents a novel stereo matching method incorporating three key innovations. Firstly, an enhanced gated recurrent unit network is introduced, accompanied by a redesigned structure to achieve higher matching accuracy. Secondly, an efficient preprocessing module is proposed, aimed at improving the algorithm’s efficiency. Lastly, in response to the challenges posed by datasets acquisition, we innovatively employed image simulation software to obtain a high-quality simulated dataset of wooden planks. To assess the feasibility of our approach, we conducted both simulated and real experiments. The experiments results clearly exhibit the superiority of our method when compared to existing approaches in terms of both stability and accuracy. In the simulation experiment, our method attained a bad1.0 score of 2.1% (compared to the baseline method’s 9.76%); In the real experiment, our method achieved an average error of 0.104 mm (compared to the baseline method’s 0.268 mm). It is worth noting that our study aims to address the challenge of acquiring datasets for deep learning and bridging the gap between simulated and real data, resulting in increased applicability of deep learning in more industrial measurement domains.

Causal inference approaches reveal both positive and negative unintended effects of agricultural and urban management practices on instream biological condition

Agricultural and urban management practices (MPs) are primarily designed and implemented to reduce nutrient and sediment concentrations in streams. However, there is growing interest in determining if MPs produce any unintended positive effects, or co-benefits, to instream biological and habitat conditions. Identifying co-benefits is challenging though because of confounding variables (i.e., those that affect both where MPs are applied and stream biota), which can be accounted for in novel causal inference approaches. Here, we used two causal inference approaches, propensity score matching (PSM) and Bayesian network learning (BNL), to identify potential MP co-benefits in the Chesapeake Bay watershed portion of Maryland, USA. Specifically, we examined how MPs may modify instream conditions that impact fish and macroinvertebrate indices of biotic integrity (IBI) and functional and taxonomic endpoints. We found evidence of positive unintended effects of MPs for both benthic macroinvertebrates and fish indicated by higher IBI scores and specific endpoints like the number of scraper macroinvertebrate taxa and lithophilic spawning fish taxa in a subset of regions. However, our results also suggest MPs have negative unintended effects, especially on sensitive benthic macroinvertebrate taxa and key instream habitat and water quality metrics like specific conductivity. Overall, our results suggest MPs offer co-benefits in some regions and catchments with largely degraded conditions but can have negative unintended effects in some regions, especially in catchments with good biological conditions. We suggest the number and types of MPs drove these mixed results and highlight carefully designed MP implementation that incorporates instream biological data at the catchment scale could facilitate co-benefits to instream biological conditions. Our study underscores the need for more research on identifying effects of individual MP types on instream biological and habitat conditions.

Towards accurate binocular vision of satellites: A cascaded multi-scale pyramid network for stereo matching on satellite imagery

Stereo matching of high-resolution satellite stereo images is a fundamental and challenging task in photogrammetry, geoscience, and remote sensing. Some deep learning-based methods have shown great potential in solving this task recently. However, these methods have not attracted much attention as their accuracy is still unsatisfactory, especially in regions with intractable factors (e.g., occlusions, repetitive patterns, low texture, non-texture, and disparity discontinuities). To tackle these challenging factors and improve disparity accuracy, we propose an end-to-end stereo matching network named Cascaded Multi-Scale Pyramid Network (CMSP-Net). Firstly, to fully utilize the multi-level spatial context information and mitigate the ambiguous matching caused by repetitive patterns, low texture, non-texture, and occlusions, a cost volume pyramid is constructed with multi-scale image features. Then, each cost volume in the pyramid is aggregated with an hourglass structure to exploit the multi-scale context in a single cost volume. Secondly, considering that high-resolution cost volumes contain more detailed information but have small receptive fields, while low-resolution ones have large receptive fields but lack details, we design an Attention-Guided Cost Fusion (AGCF) strategy to fuse pyramid cost volumes, which effectively integrates the advantages of multi-scale cost volumes while mitigating the backfiring caused by semantic inconsistency across different scales. Thirdly, a disparity refinement module is designed to improve overall disparity accuracy further, which incorporates the reconstruction error and edge clues of input satellite stereo images. Extensive experimental results on multiple satellite datasets demonstrate that the proposed method can effectively reduce matching ambiguities and recover sharp disparity discontinuities, achieving clear superiority over existing state-of-the-art methods.

Robust distance measurement using illumination map estimation and MAHNet in underground coal mines

An effective binocular stereo distance measurement method is proposed to address challenges posed by low brightness and weak texture of images captured in underground coal mines for the machine vision method. This approach is based on illumination map estimation and the MobileNetV3 attention hourglass stereo matching network (MAHNet) model. First, a binocular stereo vision system is established in which infrared LEDs are uniformly distributed on both sides of the belt conveyor bracket as visual feature points. Second, images are preprocessed using illumination map estimation, and the optimization of inhomogeneous brightness image enhancement is achieved by adopting adaptive Gamma correction. Third, the YOLOv5 target detection network and Gaussian fitting fusion algorithm are utilized to detect infrared LED feature points. Fourth, the MAHNet model is employed to generate the cost volume and perform disparity regression, resulting in the acquisition of accurate disparity images. Finally, triangulation is applied to determine the depth of feature points. The experimental results of distance measurement demonstrate that an average relative ranging accuracy of 1.52% within the range of 50.0 cm to 250.0 cm can be achieved by the optimized method, thereby validating the effectiveness of this binocular distance measurement method in underground coal mines.

A broadband single-ended active-feedforward -noise-canceling LNA with IP2 enhancement in stacked n/pMOS configurations

In this paper, we present a broadband low-noise amplifier (LNA), using active-feedforward noise-cancellation and complementary n/pMOS configurations. Based on traditional common-gate (CG) and common-source (CS) noise canceling topology, the applied active feedforward stage reduces the CG's dc current and alleviates its resistive load tradeoff between noise and headroom. Meanwhile, the active feedforward stage follows the same noise cancellation (NC) principle as the CG transistors. A low noise figure is thus obtained. In addition, the complementary n/pMOS configuration is used to cancel second-order distortions and double current efficiency. Two π-type matching networks are utilized to broaden the bandwidth of S11 and gain. After applying these techniques, an LNA prototype was designed in standard 65 nm CMOS technology. Simulation results display a gain of 14–17 dB and a noise figure (NF) of 2.45–3.45 dB within a bandwidth of 1–12 GHz. The linearity of IIP3 and IIP2 are −2.4 and 23 dBm at 5 GHz. The presented circuit consumes only 7.8 mW of dc power while occupying an area of 0.21 mm2.

Digital non-Foster-inspired electronics for broadband impedance matching

Narrow bandwidths are a general bottleneck for applications relying on passive, linear, subwavelength resonators. In the past decades, several efforts have been devoted to overcoming this challenge, broadening the bandwidth of small resonators by the means of analog non-Foster matching networks for radiators, antennas and metamaterials. However, most non-Foster approaches present challenges in terms of tunability, stability and power limitations. Here, by tuning a subwavelength acoustic transducer with digital non-Foster-inspired electronics, we demonstrate five-fold bandwidth enhancement compared to conventional analog non-Foster matching. Long-distance transmission over airborne acoustic channels, with approximately three orders of magnitude increase in power level, validates the performance of the proposed approach. We also demonstrate convenient reconfigurability of our non-Foster-inspired electronics. This implementation provides a viable solution to enhance the bandwidth of sub-wavelength resonance-based systems, extendable to the electromagnetic domain, and enables the practical implementation of airborne and underwater acoustic radiators.

Radio frequency electric field-enhanced sensing based on the Rydberg atom-based superheterodyne receiver.

We present enhanced sensing of a radio frequency (RF) electric field (E-field) by the combined polarizability of Rydberg atoms and the optimized local oscillator (LO) field of a superheterodyne receiver. Our modified theoretical model reveals the dependencies of the sensitivity of E-field amplitude measurement on the polarizability of Rydberg states and the strength of the LO field. The enhanced sensitivities of the megahertz (MHz) E-field are demonstrated at the optimal LO field for three different Rydberg states ${\rm 43D}_{5/2}$, ${\rm 60S}_{1/2}$, and ${\rm 90S}_{1/2}$. The sensitivity of 63 MHz for the ${\rm 90S}_{1/2}$ state reaches 9.6 $\times 10^{-5}\rm \,V/m/\sqrt {Hz}$, which is approximately an order of magnitude higher than those already published. This result closely approaches the sensitivity limit of a 1 cm passive dipole antenna without using an impedance matching network. This atomic sensor based on the Rydberg Stark effect with heterodyne technique is expected to boost an alternative solution to electric dipole antennas.

A novel dual‐band forward/inverse Doherty power amplifier

SummaryIn this paper, a dual‐band forward/inverse Doherty power amplifier (F/I‐DPA) based on hybrid load modulation network is proposed. The amplifier replaces the λ/4 transmission line in a conventional Doherty power amplifier (DPA) with a coupler‐based load modulation network (LMN) that incorporates a post matching network (PMN) for load modulation at the isolated ports. The LMN can realize both conventional DPA and inverse DPA load modulation methods in the operating band. In order to verify this theory, a prototype with 6 dB output power back‐off (OBO) at 3.3–3.6 GHz and 4.8–5.0 GHz was designed. The measured results indicate that the output power of the F/I‐DPA is 42–42.8 dBm and 41.4–43.4 dBm, and its saturation efficiencies are 68.1%–74.2% and 61%–72.6%, respectively. The corresponding 6‐dB OBO efficiencies is 37.4%–54.5% and 38%–49.3%, respectively.

A Multi-Information Fusion Method for Repetitive Tunnel Disease Detection

Existing tunnel defect detection methods often lack repeated inspections, limiting longitudinal analysis of defects. To address this, we propose a multi-information fusion approach for continuous defect monitoring. Initially, we utilized the You Only Look Once version 7 (Yolov7) network to identify defects in tunnel lining videos. Subsequently, defect localization is achieved with Super Visual Odometer (SuperVO) algorithm. Lastly, the SuperPoint–SuperGlue Matching Network (SpSg Network) is employed to analyze similarities among defect images. Combining the above information, the repeatability detection of the disease is realized. SuperVO was tested in tunnels of 159 m and 260 m, showcasing enhanced localization accuracy compared to traditional visual odometry methods, with errors measuring below 0.3 m on average and 0.8 m at maximum. The SpSg Network surpassed the depth-feature-based Siamese Network in image matching, achieving a precision of 96.61%, recall of 93.44%, and F1 score of 95%. These findings validate the effectiveness of this approach in the repetitive detection and monitoring of tunnel defects.

Absolute measurement of vacuum ultraviolet fluxes from inductively coupled plasmas via metal surface photoemission currents

Quantifying vacuum-ultraviolet (VUV) fluxes typically requires vacuum-compatible spectrometers and is often associated with significant cost and effort. A simple technique for the absolute measurement of local VUV fluxes from plasmas using the photoemission from a set of coated metal plates, is described. The radiant power from a 13.56 MHz hydrogen plasma operating at 40–87 mTorr and with an radio frequency (RF) input power from 100 to 120 W was investigated by irradiating a set of 2 cm diameter Au, Ag and Cu plates. The variation in photoemission currents was compared with the photoelectric yield curves to estimate the absolute flux incident on the surfaces in the 113–190 nm range. The measured fluxes were found to have an uncertainty of 5%–30% when compared with the VUV spectrometer measurements. The VUV output power was found to have a maximum at a pressure of 70–80 mTorr and to increase with RF power. In all cases, the VUV output power was measured to be approximately 12%–16% of the RF input power to the matching network, in good agreement with spectroscopy results.

A Compact GaN Power Amplifier Module for New Generation Cellular Basestations

This paper presents a compact class-AB Power Amplifier Module (PAM) designed for new generation massive Multiple Input Multiple Output (MiMo) cellular base stations. The module is designed at the center frequency of 3.5GHz targeting Long Term Evolution (LTE) and 5G New Radio (NR) bands. The module is a hybrid design that incorporates a Gallium Nitride (GaN) High Mobility-Electron Transistor (HEMT) die, discrete components-based input, and output matching networks. The entire design is realized on an 8.5 x 5.2 mm, 2-layer Rogers4003C substrate. The module is assembled on a PCB as an open-top for post-characterization tuning. The small signal and large signal measurements are in quite good agreement. The measurement results show that the amplifier is unconditionally stable, the input return loss is 12.2 dB, the output return loss is 7.7 dB, and the small signal gain is 13.4 dB. The saturated output power is 33.3 dBm with a Power Added Efficiency of 20.1%. The small signal gain drops to 11.2 dB at around 22 dBm of input power due to GaN technology’s intrinsic soft compression characteristics.

The Design and Analysis of a 25-Watt Broad-Band GaN HEMT-Based Power Amplifier

This paper presents the novel design and analysis of a 25 W broadband Class-AB GaN HEMT-based power amplifier working over 0.9–1.7 GHz. A large signal model of the Wolfspeed-make GaN HEMT CG2H40025 has been used in this design. The comprehensive design process has been carried out with the help of the Advanced Design System software by Keysight. Instead of conjugately matching the load and source impedance obtained from load-pull analysis of a nonlinear model of CG2H40025, the value of load and source impedance has been tuned with the help of a novel design approach of an ideal matching design approach. Thus, to achieve an output power of more than 25 W and a flat large signal gain of 15.425 ± 0.375 dB, a novel design approach has been employed to create input and output matching networks, maintaining a lower Q value results in broad bandwidth and for determining the load and source impedances. The circuit has been fabricated on Roger’s substrate RO4350B having a dielectric constant of 3.66 and a loss tangent of 0.0031. The unique design approach based on electromagnetic simulation of the circuit at each design step yielded experimental results that agreed very well with the simulated results. The fabricated power amplifier achieves a power-added efficiency of over 54.78% and a drain efficiency of over 55.45% throughout the entire frequency range. It also delivers a maximum output power of 32.18 W at 1.3 GHz. This power amplifier is developed for L-band Foliage Penetrating Radar.

Hourglass cascaded recurrent stereo matching network

Stereo matching acts a crucial role in computer vision and robotics applications. An accurate cost volume and robust disparity regression method are essential for stereo matching of high accuracy. Following GCNet and PSMNet, constructing 4D cost volume and then using the soft argmin method to regress has been dominated. However, it will encounter many difficulties due to the multi-modal distribution of cost volume. One of the reasons for this multi-modal distribution is the occlusion area which not be possible to find a matching region on the reference image and rarely discussed. In this paper, we propose to use global context information could improve the performance of model in occluded regions. Recently, novel recurrent neural network regression methods are proposed, but most of them regress disparity maps from 3D cost volume. In this paper, we propose the new combinatorial paradigm that combine stacked hourglass modules and recurrent neural networks to further aggregate 4D cost volume and regress disparity respectively. The proposed method can be seamlessly integrated into most stereo matching networks, we improved the accuracy by 45% for PSMNet and 38% for GwcNet in our experiment. Experimental results on Scene Flow, KITTI2012, KITTI2015, and ETH3D datasets show our method is competitive. The code is available at: https://github.com/truman1211/HCRnet.

Self-support matching networks with multiscale attention for few-shot semantic segmentation

Recent advancements in Few-shot segmentation (FSS) have displayed remarkable capabilities in predicting segmentation masks for unseen class images, using only a limited number of annotated images. However, existing methods have overlooked the influence of contextual information on segmentation and primarily rely on supporting prototypes, with limited research on query prototyping. Effectively utilizing multi-scale features and query information poses a challenging problem in this domain. To address these challenges, this paper proposes a novel approach called the multi-scale and attention-based self-support prototype few-shot semantic segmentation network (MASNet). First, a multi-scale feature enhancement module is designed to obtain features at different scales to enrich global context information. Then, simple and efficient channel attention is utilized to guide the query features related to the target class. Finally, the query prototype is matched with the query features using a self-supporting matching module. This strategy efficiently captures class-based features and addresses the issue of intra-class variance in few-shot segmentation. The experimental results on Pascal-5i, COCO-20i and Abdominal MRI datasets demonstrate that the proposed method achieves remarkable robustness and improved accuracy performance.

SEMScene: Semantic-Consistency Enhanced Multi-Level Scene Graph Matching for Image-Text Retrieval

Image-text retrieval, a fundamental cross-modal task, performs similarity reasoning for images and texts. The primary challenge for image-text retrieval is cross-modal semantic heterogeneity, where the semantic features of visual and textual modalities are rich but distinct. Scene graph is an effective representation for images and texts as it explicitly models objects and their relations. Existing scene graph based methods have not fully taken the features regarding various granularities implicit in scene graph into consideration (e.g. triplets), the inadequate feature matching incurs the absence of non-trivial semantic information (e.g. inner relations among triplets). Therefore, we propose a S emantic-Consistency E nhanced M ulti-Level Scene Graph Matching (SEMScene) network, which exploits the semantic relevance between visual and textual scene graphs from fine-grained to coarse-grained. Firstly, under the scene graph representation, we perform feature matching including low-level node matching, mid-level semantic triplet matching, and high-level holistic scene graph matching. Secondly, to enhance the semantic-consistency for object-fused triplets carrying key correlation information, we propose a dual-step constraint mechanism in mid-level matching. Thirdly, to guide the model to learn the semantic-consistency of matched image-text pairs, we devise effective loss functions for each stage of the dual-step constraint. Comprehensive experiments on Flickr30K and MS-COCO datasets demonstrate that SEMScene achieves state-of-the-art performances with significant improvements.

Segmentation and Tracking Based on Equalized Memory Matching Network and Its Application in Electric Substation Inspection

With the wide application of deep learning, power inspection technology has made great progress. However, substation inspection videos often present challenges such as complex backgrounds, uneven lighting distribution, variations in the appearance of power equipment targets, and occlusions, which increase the difficulty of object segmentation and tracking, thereby adversely affecting the accuracy and reliability of power equipment condition monitoring. In this paper, a pixel-level equalized memory matching network (PEMMN) for power intelligent inspection segmentation and tracking is proposed. Firstly, an equalized memory matching network is designed to collect historical information about the target using a memory bank, in which a pixel-level equalized matching method is used to ensure that the reference frame information can be transferred to the current frame reliably, guiding the segmentation tracker to focus on the most informative region in the current frame. Then, to prevent memory explosion and the accumulation of segmentation template errors, a mask quality evaluation module is introduced to obtain the confidence level of the current segmentation result so as to selectively store the frames with high segmentation quality to ensure the reliability of the memory update. Finally, the synthetic feature map generated by the PEMMN and the mask quality assessment strategy are unified into the segmentation tracking framework to achieve accurate segmentation and robust tracking. Experimental results show that the method performs excellently on real substation inspection scenarios and three generalized datasets and has high practical value.

Viruses contribute to microbial diversification in the rumen ecosystem and are associated with certain animal production traits

BackgroundThe rumen microbiome enables ruminants to digest otherwise indigestible feedstuffs, thereby facilitating the production of high-quality protein, albeit with suboptimal efficiency and producing methane. Despite extensive research delineating associations between the rumen microbiome and ruminant production traits, the functional roles of the pervasive and diverse rumen virome remain to be determined.ResultsLeveraging a recent comprehensive rumen virome database, this study analyzes virus-microbe linkages, at both species and strain levels, across 551 rumen metagenomes, elucidating patterns of microbial and viral diversity, co-occurrence, and virus-microbe interactions. Additionally, this study assesses the potential role of rumen viruses in microbial diversification by analyzing prophages found in rumen metagenome-assembled genomes. Employing CRISPR–Cas spacer-based matching and virus-microbe co-occurrence network analysis, this study suggests that the viruses in the rumen may regulate microbes at strain and community levels through both antagonistic and mutualistic interactions. Moreover, this study establishes that the rumen virome demonstrates responsiveness to dietary shifts and associations with key animal production traits, including feed efficiency, lactation performance, weight gain, and methane emissions.ConclusionsThese findings provide a substantive framework for further investigations to unravel the functional roles of the virome in the rumen in shaping the microbiome and influencing overall animal production performance.3QAbSJqYZPn2njEBJ23VpAVideo

Design and operation of a load-tolerant ICRH system in Experimental Advanced Superconducting Tokamak

Ion Cyclotron Resonance Heating (ICRH) has been a dependable tool for sturdy plasma heating with high RF power of several megawatts. However, a sudden increase in the reflected power during ICRH heating experiments is a problem that should be solved for future fusion experimental devices. To solve this issue, a load tolerant matching network has been designed for the ICRH system in EAST. The matching network includes a 3-stub tuner impedance matching system with conjugate-T structure, 30 Ω to 50 Ω transmission line and center grounded antenna strap. By maintaining a low reflection ratio in the network for a wide range of resistance, this matching network can allow sturdy high-power operations without fast impedance matching in EAST. In our matching network, the two arms of a conjugate-T are designed to have a λ/2 length difference which could mitigate current imbalance and antenna poloidal phasing outside of the control problem. The T-point corresponds to the maximum point of the standing wave voltage, which could greatly improve the input impedance of the antenna.

Miniaturized design of multi-octave PA using spoof surface plasmon polaritons

Surface Plasmon Polariton (SSPP), which exhibits subwavelength-scaled field confinement, can be realized at microwave frequencies by ultrathin corrugated metallic strips, providing significant potential for circuit and system miniaturization. A number of SSPP units were employed in this study to design input and output matching networks of a multi-octave RF power amplifier (PA) for the purpose of reducing the overall circuit size. The designed SSPP-based PAs were fabricated and demonstrated to have an output power between 39.1 dBm and 41.8 dBm, and a power added efficiency (PAE) ranging between 60.2 % and 69.8 % in the frequency range of 0.8 GHz to 3.1 GHz, with a size of 35.5 mm * 46.7 mm, which achieves a 47 % size reduction compared to the traditional transmission-line based PA. A highly efficient global optimization method, the Bayesian Optimization (BO), was utilized to further enhance performance. SSPP PA's average output power and PAE have been improved by approximately 0.3 dBm and 2.6 %, respectively. Its overall size remains at the same level. With the use of a 20 MHz 5GNR signal, digital pre-distortion (DPD) has been implemented, and the linearity of the PA has been improved.