Regular inspection of bridge cracks is crucial to bridge maintenance and repair.The traditional manual crack detection methods are timeconsuming,dangerous and subjective.At the same time,for the existing mainstream vi...Regular inspection of bridge cracks is crucial to bridge maintenance and repair.The traditional manual crack detection methods are timeconsuming,dangerous and subjective.At the same time,for the existing mainstream vision-based automatic crack detection algorithms,it is challenging to detect fine cracks and balance the detection accuracy and speed.Therefore,this paper proposes a new bridge crack segmentationmethod based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+network framework.First,the improved lightweight MobileNetv2 network and dilated separable convolution are integrated into the original DeeplabV3+network to improve the original backbone network Xception and atrous spatial pyramid pooling(ASPP)module,respectively,dramatically reducing the number of parameters in the network and accelerates the training and prediction speed of the model.Moreover,we introduce the parallel attention mechanism into the encoding and decoding stages.The attention to the crack regions can be enhanced from the aspects of both channel and spatial parts and significantly suppress the interference of various noises.Finally,we further improve the detection performance of the model for fine cracks by introducing a multi-scale features fusion module.Our research results are validated on the self-made dataset.The experiments show that our method is more accurate than other methods.Its intersection of union(IoU)and F1-score(F1)are increased to 77.96%and 87.57%,respectively.In addition,the number of parameters is only 4.10M,which is much smaller than the original network;also,the frames per second(FPS)is increased to 15 frames/s.The results prove that the proposed method fits well the requirements of rapid and accurate detection of bridge cracks and is superior to other methods.展开更多
In order to improve the detection accuracy of small objects,a neighborhood fusion-based hierarchical parallel feature pyramid network(NFPN)is proposed.Unlike the layer-by-layer structure adopted in the feature pyramid...In order to improve the detection accuracy of small objects,a neighborhood fusion-based hierarchical parallel feature pyramid network(NFPN)is proposed.Unlike the layer-by-layer structure adopted in the feature pyramid network(FPN)and deconvolutional single shot detector(DSSD),where the bottom layer of the feature pyramid network relies on the top layer,NFPN builds the feature pyramid network with no connections between the upper and lower layers.That is,it only fuses shallow features on similar scales.NFPN is highly portable and can be embedded in many models to further boost performance.Extensive experiments on PASCAL VOC 2007,2012,and COCO datasets demonstrate that the NFPN-based SSD without intricate tricks can exceed the DSSD model in terms of detection accuracy and inference speed,especially for small objects,e.g.,4%to 5%higher mAP(mean average precision)than SSD,and 2%to 3%higher mAP than DSSD.On VOC 2007 test set,the NFPN-based SSD with 300×300 input reaches 79.4%mAP at 34.6 frame/s,and the mAP can raise to 82.9%after using the multi-scale testing strategy.展开更多
We consider a parallel decentralized detection system employing a bank of local detectors(LDs)to access a commonly-observed phenomenon.The system makes a binary decision about the phenomenon,accepting one of two hypot...We consider a parallel decentralized detection system employing a bank of local detectors(LDs)to access a commonly-observed phenomenon.The system makes a binary decision about the phenomenon,accepting one of two hypotheses(H_(0)("absent")or H_(1)("present")).The kth LD uses a local decision rule to compress its local observations yk into a binary local decision uk;uk=0 if the kth LD accepts H_(0)and uk=1 if it accepts H_(1).The kth LD sends its decision uk over a noiseless dedicated channel to a Data Fusion Center(DFC).The DFC combines the local decisions it receives from n LDs(u_(1),u_(2),...,u_(n))into a single binary global decision u_(0)(u_(0)=0 for accepting H_(0)or u_(0)=1 for accepting H_(1)).If each LD uses a single deterministic local decision rule(calculating uk from the local observations yk)and the DFC uses a single deterministic global decision rule(calculating u_(0)from the n local decisions),the team receiver operating characteristic(ROC)curve is in general non-concave.The system's performance under a Neyman-Pearson criterion may then be suboptimal in the sense that a mixed strategy may yield a higher probability of detection when the probability of false alarm is constrained not to exceed a certain value,α>0.Specifically,a"dependent randomization"detection scheme can be applied in certain circumstances to improve the system's performance by making the ROC curve concave.This scheme requires a coordinated and synchronized action between the DFC and the LDs.In this study,we specify when dependent randomization is needed,and discuss the proper response of the detection system if synchronization between the LDs and the DFC is temporarily lost.展开更多
Sputum smear tests are critical for the diagnosis of respiratory diseases. Automatic segmentation of bacteria from spu-tum smear images is important for improving diagnostic efficiency. However, this remains a challen...Sputum smear tests are critical for the diagnosis of respiratory diseases. Automatic segmentation of bacteria from spu-tum smear images is important for improving diagnostic efficiency. However, this remains a challenging task owing to the high interclass similarity among different categories of bacteria and the low contrast of the bacterial edges. To explore more levels of global pattern features to promote the distinguishing ability of bacterial categories and main-tain sufficient local fine-grained features to ensure accurate localization of ambiguous bacteria simultaneously, we propose a novel dual-branch deformable cross-attention fusion network (DB-DCAFN) for accurate bacterial segmen-tation. Specifically, we first designed a dual-branch encoder consisting of multiple convolution and transformer blocks in parallel to simultaneously extract multilevel local and global features. We then designed a sparse and deformable cross-attention module to capture the semantic dependencies between local and global features, which can bridge the semantic gap and fuse features effectively. Furthermore, we designed a feature assignment fusion module to enhance meaningful features using an adaptive feature weighting strategy to obtain more accurate segmentation. We conducted extensive experiments to evaluate the effectiveness of DB-DCAFN on a clinical dataset comprising three bacterial categories: Acinetobacter baumannii, Klebsiella pneumoniae, and Pseudomonas aeruginosa. The experi-mental results demonstrate that the proposed DB-DCAFN outperforms other state-of-the-art methods and is effective at segmenting bacteria from sputum smear images.展开更多
SimCSE框架仅使用分类令牌[CLS]token作为文本向量,同时忽略基座模型内层级信息,导致对基座模型输出语义特征提取不充分.本文基于SimCSE框架提出一种融合预训练模型层级特征方法SimCSE-HFF(SimCSE with hierarchical feature fusion,Sim...SimCSE框架仅使用分类令牌[CLS]token作为文本向量,同时忽略基座模型内层级信息,导致对基座模型输出语义特征提取不充分.本文基于SimCSE框架提出一种融合预训练模型层级特征方法SimCSE-HFF(SimCSE with hierarchical feature fusion,SimCSE-HFF).SimCSE-HFF基于双路并行网络,使用短路径和长路径强化特征学习,短路径使用卷积神经网络学习文本局部特征并进行降维,长路径使用双向门控循环神经网络学习深度语义信息,同时在长路径中利用自编码器融合基座模型内部其他层特征,解决模型对输出特征提取不充分的问题.在STS-B的中文与英文数据集上,SimCSE-HFF方法效果在语义相似度Spearman和Pearson相关性指标上优于传统方法,在不同预训练模型上均得到提升;在下游任务检索问答上也优于SimCSE框架,具有更优秀的通用性.展开更多
A decentralized parallel one-pass deconvolution algorithm for multisensor systems with multiplicative noises is proposed. Comparing with the conventional deconvolution algorithm, it avoids the computational overload a...A decentralized parallel one-pass deconvolution algorithm for multisensor systems with multiplicative noises is proposed. Comparing with the conventional deconvolution algorithm, it avoids the computational overload and the high storage requirement. The algorithm is optimal in the sense of linear minimum-variance. The simulation results illustrate the validity of the proposed algorithm.展开更多
基金This work was supported by the High-Tech Industry Science and Technology Innovation Leading Plan Project of Hunan Provincial under Grant 2020GK2026,author B.Y,http://kjt.hunan.gov.cn/.
文摘Regular inspection of bridge cracks is crucial to bridge maintenance and repair.The traditional manual crack detection methods are timeconsuming,dangerous and subjective.At the same time,for the existing mainstream vision-based automatic crack detection algorithms,it is challenging to detect fine cracks and balance the detection accuracy and speed.Therefore,this paper proposes a new bridge crack segmentationmethod based on parallel attention mechanism and multi-scale features fusion on top of the DeeplabV3+network framework.First,the improved lightweight MobileNetv2 network and dilated separable convolution are integrated into the original DeeplabV3+network to improve the original backbone network Xception and atrous spatial pyramid pooling(ASPP)module,respectively,dramatically reducing the number of parameters in the network and accelerates the training and prediction speed of the model.Moreover,we introduce the parallel attention mechanism into the encoding and decoding stages.The attention to the crack regions can be enhanced from the aspects of both channel and spatial parts and significantly suppress the interference of various noises.Finally,we further improve the detection performance of the model for fine cracks by introducing a multi-scale features fusion module.Our research results are validated on the self-made dataset.The experiments show that our method is more accurate than other methods.Its intersection of union(IoU)and F1-score(F1)are increased to 77.96%and 87.57%,respectively.In addition,the number of parameters is only 4.10M,which is much smaller than the original network;also,the frames per second(FPS)is increased to 15 frames/s.The results prove that the proposed method fits well the requirements of rapid and accurate detection of bridge cracks and is superior to other methods.
基金The National Natural Science Foundation of China(No.61603091)。
文摘In order to improve the detection accuracy of small objects,a neighborhood fusion-based hierarchical parallel feature pyramid network(NFPN)is proposed.Unlike the layer-by-layer structure adopted in the feature pyramid network(FPN)and deconvolutional single shot detector(DSSD),where the bottom layer of the feature pyramid network relies on the top layer,NFPN builds the feature pyramid network with no connections between the upper and lower layers.That is,it only fuses shallow features on similar scales.NFPN is highly portable and can be embedded in many models to further boost performance.Extensive experiments on PASCAL VOC 2007,2012,and COCO datasets demonstrate that the NFPN-based SSD without intricate tricks can exceed the DSSD model in terms of detection accuracy and inference speed,especially for small objects,e.g.,4%to 5%higher mAP(mean average precision)than SSD,and 2%to 3%higher mAP than DSSD.On VOC 2007 test set,the NFPN-based SSD with 300×300 input reaches 79.4%mAP at 34.6 frame/s,and the mAP can raise to 82.9%after using the multi-scale testing strategy.
文摘We consider a parallel decentralized detection system employing a bank of local detectors(LDs)to access a commonly-observed phenomenon.The system makes a binary decision about the phenomenon,accepting one of two hypotheses(H_(0)("absent")or H_(1)("present")).The kth LD uses a local decision rule to compress its local observations yk into a binary local decision uk;uk=0 if the kth LD accepts H_(0)and uk=1 if it accepts H_(1).The kth LD sends its decision uk over a noiseless dedicated channel to a Data Fusion Center(DFC).The DFC combines the local decisions it receives from n LDs(u_(1),u_(2),...,u_(n))into a single binary global decision u_(0)(u_(0)=0 for accepting H_(0)or u_(0)=1 for accepting H_(1)).If each LD uses a single deterministic local decision rule(calculating uk from the local observations yk)and the DFC uses a single deterministic global decision rule(calculating u_(0)from the n local decisions),the team receiver operating characteristic(ROC)curve is in general non-concave.The system's performance under a Neyman-Pearson criterion may then be suboptimal in the sense that a mixed strategy may yield a higher probability of detection when the probability of false alarm is constrained not to exceed a certain value,α>0.Specifically,a"dependent randomization"detection scheme can be applied in certain circumstances to improve the system's performance by making the ROC curve concave.This scheme requires a coordinated and synchronized action between the DFC and the LDs.In this study,we specify when dependent randomization is needed,and discuss the proper response of the detection system if synchronization between the LDs and the DFC is temporarily lost.
基金the Natural Science Foundation of Shandong Province,No.ZR2021MH213and in part by the Suzhou Science and Technology Bureau,No.SJC2021023.
文摘Sputum smear tests are critical for the diagnosis of respiratory diseases. Automatic segmentation of bacteria from spu-tum smear images is important for improving diagnostic efficiency. However, this remains a challenging task owing to the high interclass similarity among different categories of bacteria and the low contrast of the bacterial edges. To explore more levels of global pattern features to promote the distinguishing ability of bacterial categories and main-tain sufficient local fine-grained features to ensure accurate localization of ambiguous bacteria simultaneously, we propose a novel dual-branch deformable cross-attention fusion network (DB-DCAFN) for accurate bacterial segmen-tation. Specifically, we first designed a dual-branch encoder consisting of multiple convolution and transformer blocks in parallel to simultaneously extract multilevel local and global features. We then designed a sparse and deformable cross-attention module to capture the semantic dependencies between local and global features, which can bridge the semantic gap and fuse features effectively. Furthermore, we designed a feature assignment fusion module to enhance meaningful features using an adaptive feature weighting strategy to obtain more accurate segmentation. We conducted extensive experiments to evaluate the effectiveness of DB-DCAFN on a clinical dataset comprising three bacterial categories: Acinetobacter baumannii, Klebsiella pneumoniae, and Pseudomonas aeruginosa. The experi-mental results demonstrate that the proposed DB-DCAFN outperforms other state-of-the-art methods and is effective at segmenting bacteria from sputum smear images.
文摘SimCSE框架仅使用分类令牌[CLS]token作为文本向量,同时忽略基座模型内层级信息,导致对基座模型输出语义特征提取不充分.本文基于SimCSE框架提出一种融合预训练模型层级特征方法SimCSE-HFF(SimCSE with hierarchical feature fusion,SimCSE-HFF).SimCSE-HFF基于双路并行网络,使用短路径和长路径强化特征学习,短路径使用卷积神经网络学习文本局部特征并进行降维,长路径使用双向门控循环神经网络学习深度语义信息,同时在长路径中利用自编码器融合基座模型内部其他层特征,解决模型对输出特征提取不充分的问题.在STS-B的中文与英文数据集上,SimCSE-HFF方法效果在语义相似度Spearman和Pearson相关性指标上优于传统方法,在不同预训练模型上均得到提升;在下游任务检索问答上也优于SimCSE框架,具有更优秀的通用性.
基金This work was supported by the Science&Technology Research Key Projects of Ministry of Education of China.
文摘A decentralized parallel one-pass deconvolution algorithm for multisensor systems with multiplicative noises is proposed. Comparing with the conventional deconvolution algorithm, it avoids the computational overload and the high storage requirement. The algorithm is optimal in the sense of linear minimum-variance. The simulation results illustrate the validity of the proposed algorithm.
