FIBTNet:Building Change Detection for Remote Sensing Images Using Feature Interactive Bi-Temporal Network

In this paper,a feature interactive bi-temporal change detection network(FIBTNet)is designed to solve the problem of pseudo change in remote sensing image building change detection.The network improves the accuracy of change detection through bi-temporal feature interaction.FIBTNet designs a bi-temporal feature exchange architecture(EXA)and a bi-temporal difference extraction architecture(DFA).EXA improves the feature exchange ability of the model encoding process through multiple space,channel or hybrid feature exchange methods,while DFA uses the change residual(CR)module to improve the ability of the model decoding process to extract different features at multiple scales.Additionally,at the junction of encoder and decoder,channel exchange is combined with the CR module to achieve an adaptive channel exchange,which further improves the decision-making performance of model feature fusion.Experimental results on the LEVIR-CD and S2Looking datasets demonstrate that iCDNet achieves superior F1 scores,Intersection over Union(IoU),and Recall compared to mainstream building change detectionmodels,confirming its effectiveness and superiority in the field of remote sensing image change detection.

Joint Rain Streaks & Haze Removal Network for Object Detection

In the realm of low-level vision tasks,such as image deraining and dehazing,restoring images distorted by adverse weather conditions remains a significant challenge.The emergence of abundant computational resources has driven the dominance of deep Convolutional Neural Networks(CNNs),supplanting traditional methods reliant on prior knowledge.However,the evolution of CNN architectures has tended towards increasing complexity,utilizing intricate structures to enhance performance,often at the expense of computational efficiency.In response,we propose the Selective Kernel Dense Residual M-shaped Network(SKDRMNet),a flexible solution adept at balancing computational efficiency with network accuracy.A key innovation is the incorporation of an M-shaped hierarchical structure,derived from the U-Net framework as M-Network(M-Net),within which the Selective Kernel Dense Residual Module(SDRM)is introduced to reinforce multi-scale semantic feature maps.Our methodology employs two sampling techniques-bilinear and pixel unshuffled and utilizes a multi-scale feature fusion approach to distil more robust spatial feature map information.During the reconstruction phase,feature maps of varying resolutions are seamlessly integrated,and the extracted features are effectively merged using the Selective Kernel Fusion Module(SKFM).Empirical results demonstrate the comprehensive superiority of SKDRMNet across both synthetic and real rain and haze datasets.

A 532 nm molecular iodine optical frequency standard based on modulation transfer spectroscopy

We report construction of an iodine-stabilized laser frequency standard at 532 nm based on modulation transfer spectroscopy(MTS)technology with good reproducibility.A frequency stability of 2.5×10^(-14)at 1 s averaging time is achieved,and the frequency reproducibility has a relative uncertainty of 3.5×10^(-13),demonstrating the great stability of our setup.The systematic uncertainty of the iodine-stabilized laser frequency standard is evaluated,especially the contribution of the residual amplitude modulation(RAM).The contribution of the RAM in MTS cannot be evaluated directly.To solve this problem,we theoretically deduce the MTS signal with RAM under large modulation depth,and prove that the non-symmetric shape of the MTS signal is directly related to the MTS effect.The non-symmetric shape factor can be calibrated with a frequency comb,and in real experiments,this value can be obtained by least-squares fitting of the MTS signal,from which we can infer the RAMinduced frequency shift.The full frequency uncertainty is evaluated to be 5.3 kHz(corresponding to a relative frequency uncertainty of 9.4×10^(-12)).The corrected transition frequency has a difference from the BIPM-recommended value of 2 kHz,which is within 1σ uncertainty,proving the validity of our evaluation.

Multitask Learning with Multiscale Residual Attention for Brain Tumor Segmentation and Classification

Automatic segmentation and classification of brain tumors are of great importance to clinical treatment.However,they are challenging due to the varied and small morphology of the tumors.In this paper,we propose a multitask multiscale residual attention network(MMRAN)to simultaneously solve the problem of accurately segmenting and classifying brain tumors.The proposed MMRAN is based on U-Net,and a parallel branch is added at the end of the encoder as the classification network.First,we propose a novel multiscale residual attention module(MRAM)that can aggregate contextual features and combine channel attention and spatial attention better and add it to the shared parameter layer of MMRAN.Second,we propose a method of dynamic weight training that can improve model performance while minimizing the need for multiple experiments to determine the optimal weights for each task.Finally,prior knowledge of brain tumors is added to the postprocessing of segmented images to further improve the segmentation accuracy.We evaluated MMRAN on a brain tumor data set containing meningioma,glioma,and pituitary tumors.In terms of segmentation performance,our method achieves Dice,Hausdorff distance(HD),mean intersection over union(MIoU),and mean pixel accuracy(MPA)values of 80.03%,6.649 mm,84.38%,and 89.41%,respectively.In terms of classification performance,our method achieves accuracy,recall,precision,and F1-score of 89.87%,90.44%,88.56%,and 89.49%,respectively.Compared with other networks,MMRAN performs better in segmentation and classification,which significantly aids medical professionals in brain tumor management.The code and data set are available at https://github.com/linkenfaqiu/MMRAN.

Residual intensity modulation in resonator fiber optic gyros with sinusoidal wave phase modulation

We present how residual intensity modulation(RIM) affects the performance of a resonator fiber optic gyro(R-FOG) through a sinusoidal wave phase modulation technique. The expression for the R-FOG system's demodulation curve under RIM is obtained. Through numerical simulation with different RIM coefficients and modulation frequencies, we find that a zero deviation is induced by the RIM effect on the demodulation curve, and this zero deviation varies with the RIM coefficient and modulation frequency. The expression for the system error due to this zero deviation is derived. Simulation results show that the RIM-induced error varies with the RIM coefficient and modulation frequency. There also exists optimum values for the RIM coefficient and modulation frequency to totally eliminate the RIM-induced error, and the error increases as the RIM coefficient or modulation frequency deviates from its optimum value; however, in practical situations, these two parameters would not be exactly fixed but fluctuate from their respective optimum values, and a large system error is induced even if there exists a very small deviation of these two critical parameters from their optimum values. Simulation results indicate that the RIM-induced error should be considered when designing and evaluating an R-FOG system.

Multipath affinage stacked-hourglass networks for human pose estimation

Recently,stacked hourglass network has shown outstanding performance in human pose estimation.However,repeated bottom-up and top-down stride convolution operations in deep convolutional neural networks lead to a significant decrease in the initial image resolution.In order to address this problem,we propose to incorporate affinage module and residual attention module into stacked hourglass network for human pose estimation.This paper introduces a novel network architecture to replace the stacked hourglass network of up-sampling operation for getting high-resolution features.We refer to the architecture as an affinage module which is critical to improve the performance of the stacked hourglass network.Additionally,we also propose a novel residual attention module to increase the supervision of up-sample process.The effectiveness of the introduced module is evaluated on standard benchmarks.Various experimental results demonstrated that our method can achieve more accurate and more robust human pose estimation results in images with complex background.