检索结果-内蒙古大学图书馆

A full-scale hierarchical encoder-decoder network with cascading edge-prior for infrared and visible image fusion

PATTERN RECOGNITION 2024年 148卷

作者： Luo, Xiaoqing Wang, Juan Zhang, Zhancheng Wu, Xiao-jun Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Peoples R China Jiangnan Univ Inst Adv Technol Wuxi 214122 Peoples R China Suzhou Univ Sci & Technol Coll Elect & Informat Engn Suzhou 215009 Peoples R China

Most existing deep learning-based infrared and visible image fusion methods always fail to consider the full-scale long-range correlation and the prior knowledge, resulting in the fused images with low-contrast salient objects and blurred edge details. To overcome these drawbacks, a full-scale hierarchical encoder-decoder network with cascading edge-prior for infrared and visible image fusion is proposed. First, a top-down encoder extracts the hierarchical representations from source image. Then, to inject edge priors into the network and capture the progressive semantic correlations, a triple fusion mechanism is proposed including edge image fusion based on maximum fusion strategy, single-scale shallow layer fusion and full-scale semantic layer fusion based on dualattention fusion (DAF) strategy. The fused full-scale semantic features (F2SF) are obtained by capturing the long-range affinities of the full-scale. At the same time, a cascading edge-prior branch (CEPB) is designed to embed the fused edge knowledge into fused single-scale shallow features, jointly guiding the decoder to focus on abundant details layer-by-layer on the basis of F2SF, thus recovering the edge and texture details of the fused image well. Finally, a novel loss function consisting of SSIM, intensity and edge loss is constructed to further maintain the network with better edge representation and reconstruction capability. Compared with existing state-of-the-art fusion methods, the proposed method has better performance in terms of both visual evaluation and objective evaluation on public datasets. The source code is available at https://***/lxq-jnu/FSFu sion.

关键词： Full-scale Long-range Progressive semantic Edge-prior encoder-decoder Infrared and visible image fusion

来源：评论

学校读者我要写书评

暂无评论

LiT and Lean: Distilling Listwise Rerankers Into encoder-decoder Models 47th

LiT and Lean: Distilling Listwise Rerankers Into Encoder-De...

引用

47th European Conference on Information Retrieval, ECIR 2025

作者： Tamber, Manveer Singh Pradeep, Ronak Lin, Jimmy David R. Cheriton School of Computer Science University of Waterloo WaterlooON Canada

ISBN: (纸本)9783031887130

Large-scale LLMs have driven listwise reranking research, achieving impressive state-of-the-art results. However, their massive parameter counts and limited context sizes limit efficient reranking. To address this, we present LiT5, a family of efficient listwise rerankers based on the T5 model. Our approach demonstrates competitive reranking effectiveness compared to listwise LLM rerankers, with far fewer parameters, greater computational efficiency, and the ability to rerank more passages in a single shot. Our models consistently deliver strong effectiveness with as few as 220M parameters, offering a scalable solution for listwise reranking. Code and scripts for reproducibility are available at https://***/castorini/rank_llm. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Efficient Reranking encoder-decoder Listwise Reranking

来源：评论

学校读者我要写书评

暂无评论

An encoder-decoder Architecture within a Classical Signal-Processing Framework for Real-Time Barcode Segmentation

引用

SENSORS 2023年第13期23卷 6109页

作者： Gomez-Cardenes, Oscar Marichal-Hernandez, Jose Gil Son, Jung-Young Jimenez, Rafael Perez Rodriguez-Ramos, Jose Manuel Univ La Laguna Dept Ind Engn San Cristobal la Laguna 38200 Spain Konyang Univ Biomed Engn Dept Nonsan Si 320711 South Korea Univ Las Palmas Gran Canaria Inst Technol Dev & Innovat Commun Las Palmas Gran Canaria 35017 Spain Wooptix SL Res & Dev Dept San Cristobal la Laguna 38204 Spain

In this work, two methods are proposed for solving the problem of one-dimensional barcode segmentation in images, with an emphasis on augmented reality (AR) applications. These methods take the partial discrete Radon transform as a building block. The first proposed method uses overlapping tiles for obtaining good angle precision while maintaining good spatial precision. The second one uses an encoder-decoder structure inspired by state-of-the-art convolutional neural networks for segmentation while maintaining a classical processing framework, thus not requiring training. It is shown that the second method's processing time is lower than the video acquisition time with a 1024 x 1024 input on a CPU, which had not been previously achieved. The accuracy it obtained on datasets widely used by the scientific community was almost on par with that obtained using the most-recent state-of-the-art methods using deep learning. Beyond the challenges of those datasets, the method proposed is particularly well suited to image sequences taken with short exposure and exhibiting motion blur and lens blur, which are expected in a real-world AR scenario. Two implementations of the proposed methods are made available to the scientific community: one for easy prototyping and one optimised for parallel implementation, which can be run on desktop and mobile phone CPUs.

关键词： Radon transform scale-space methods multiscale DRT barcodes encoder-decoder pixelwise segmentation classical signal processing

来源：评论

学校读者我要写书评

暂无评论

Displacement prediction model for high arch dams using long short-term memory based encoder-decoder with dual-stage attention considering measured dam temperature

引用

ENGINEERING STRUCTURES 2023年第1期280卷

作者： Huang, Ben Kang, Fei Li, Junjie Wang, Feng Dalian Univ Technol Fac Infrastruct Engn Sch Hydraul Engn Dalian 116024 Peoples R China Hohai Univ Coll Water Conservancy & Hydropower Engn Nanjing 210098 Peoples R China China Three Gorges Univ Coll Hydraul & Environm Engn Yichang 443002 Peoples R China

Structural health monitoring method can provide important information to evaluate operational status of con-crete dams, by establishing accurate models to predict concrete dam behavior with monitored data. This study proposed a model using encoder-decoder based on long short-term memory network with dual-stage attention mechanism (DALSTM) to predict the displacement of concrete arch dams. encoder-decoder based on long short -term memory network is a deep learning technique that can perform time series prediction, and dual-stage attention mechanism focuses on the key information in the dam displacement series to improve the perfor-mance. The effectiveness and accuracy of the proposed prediction model are analyzed on a high arch dam using measured temperature in the dam body instead of the seasonal functions to represent the thermal effect. Compared with traditional stepwise regression, multiple linear regression models, radial basis function networks, and other deep learning models, results show that the proposed approach performance is more accurate and robust for dam health monitoring.

关键词： Structural health monitoring Dam behavior prediction High arch dam encoder-decoder Long short -term memory networks Dual-stage attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning to Identify Hydrologic Signatures With an encoder-decoder Framework

引用

WATER RESOURCES RESEARCH 2023年第3期59卷 e2022WR033091-e2022WR033091页

作者： Botterill, Tom E. E. McMillan, Hilary K. K. San Diego State Univ Dept Geog San Diego CA 92182 USA

Hydrologic signatures are quantitative metrics that describe a streamflow time series. Examples include annual maximum flow, baseflow index and recession shape descriptors. In this paper, we use machine learning (ML) to learn encodings that are optimal ML equivalents of hydrologic signatures, and that are derived directly from the data. We compare the learned signatures to classical signatures, interpret their meaning, and use them to build rainfall-runoff models in otherwise ungauged watersheds. Our model has an encoder-decoder structure. The encoder is a convolutional neural net mapping historical flow and climate data to a low-dimensional vector encoding, analogous to hydrological signatures. The decoder structure includes stores and fluxes similar to a classical hydrologic model. For each timestep, the decoder uses current climate data, watershed attributes and the encoding to predict coefficients that distribute precipitation between stores and store outflow coefficients. The model is trained end-to-end on the U.S. CAMELS watershed data set to minimize streamflow error. We show that learned signatures can extract new information from streamflow series, because using learned signatures as input to the process-informed model improves prediction accuracy over benchmark configurations that use classical signatures or no signatures. We interpret learned signatures by correlation with classical signatures, and by using sensitivity analysis to assess their impact on modeled store dynamics. Learned signatures are spatially correlated and relate to streamflow dynamics including seasonality, high and low extremes, baseflow and recessions. We conclude that process-informed ML models and other applications using hydrologic signatures may benefit from replacing expert-selected signatures with learned signatures.

关键词： hydrologic signature flow metric flow indices machine learning deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Deep encoder-decoder Network for Lane-Following on Autonomous Vehicle

Deep Encoder-Decoder Network for Lane-Following on Autonomou...

引用

IEEE International Conference on Consumer Electronics - Taiwan (ICCE-TW)

作者： Khanum, Abida Lee, Chao-Yang Yang, Chu-Sing Natl Cheng Kung Univ Dept Elect Engn Tainan Taiwan Natl Formosa Univ Dept Aeronaut Engn Huwei Yunlin Taiwan

ISBN: (数字)9781665470506

ISBN: (纸本)9781665470506

Nowadays there is a vast interest in a self-driving car from both academia and industry. The main reason behind recently enormous progress in deep learning approaches for an autonomous vehicle. The main objective of this research is to propose a deep hybrid encoder-decoder network with input multi-modal data to predict the decision-making task. Therefore, the proposed approaches are tested by both real and simulation data but in the real data single camera image and simulator data three-camera image data. The proposed method analyzes the effects of input data. The experiment results in analyses in terms of Computational time as-well-as parameters in which values of the steering wheel and brake both real and simulated data are (6ms and 9ms) respectively. The analysis shows that our method performs well in driving action prediction.

关键词： Deep learning encoder-decoder Autonomous Vehicle Lane-following

来源：评论

学校读者我要写书评

暂无评论

Water Quality Prediction Based on the KF-LSTM encoder-decoder Network: A Case Study with Missing Data Collection

引用

WATER 2023年第14期15卷 2542页

作者： Cai, Hao Zhang, Chen Xu, Jianlong Wang, Fei Xiao, Lianghong Huang, Shanxing Zhang, Yufeng Shantou Univ Dept Comp Sci Shantou Peoples R China Guangdong Prov Shantou Ecol Environm Monitoring Ce Shantou 515057 Peoples R China

This paper focuses on water quality prediction in the presence of a large number of missing values in water quality monitoring data. Current water quality monitoring data mostly come from different monitoring stations in different water bodies. As the duration of water quality monitoring increases, the complexity of water quality data also increases, and missing data is a common and difficult to avoid problem in water quality monitoring. In order to fully exploit the valuable features of the monitored data and improve the accuracy of water quality prediction models, we propose a long short-term memory (LSTM) encoder-decoder model that combines a Kalman filter (KF) with an attention mechanism. The Kalman filter in the model can quickly complete the reconstruction and pre-processing of hydrological data. The attention mechanism is added between the decoder and the encoder to solve the problem that traditional recursive neural network models lose long-range information and fully exploit the interaction information among high-dimensional covariate data. Using original data from the Haimen Bay water quality monitoring station in the Lianjiang River Basin for analysis, we trained and tested our model using detection data from 1 January 2019 to 30 June 2020 to predict future water quality. The results show that compared with traditional LSTM models, KF-LSTM models reduce the average absolute error (MAE) by 10%, the mean square error (MSE) by 21.2%, the root mean square error (RMSE) by 13.2%, while increasing the coefficient of determination (R2) by 4.5%. This model is more suitable for situations where there are many missing values in water quality data, while providing new solutions for real-time management of urban aquatic environments.

关键词： Kalman filter LSTM encoder-decoder time series prediction water quality prediction attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A quantile-based encoder-decoder framework for multi-step ahead runoff forecasting

引用

JOURNAL OF HYDROLOGY 2023年第1期619卷

作者： Jahangir, Mohammad Sina You, John Quilty, John Univ Waterloo Dept Civil & Environm Engn Waterloo ON Canada

Deep neural network (DNN) models have become increasingly popular in the hydrology community. However, most studies are related to (rainfall-) runoff simulation and comparatively fewer studies have focused on runoff forecasting. In this study, quantile-based (q = 0.05, 0.5, 0.95) encoder-decoder (ED) models that use long short -term memory network (LSTM) and dense network (DN) blocks were developed for three and five days ahead runoff forecasting. Through linear (LW) and non-linear (NLW) wavelet selection, hybrid models LSTM-DN, LSTM-DN-LW, LSTM-DN-NLW, ED, ED-LW, and ED-NLW were developed. For each lead time (LT = 3, 5) and value of q, different model configurations were created using different input lag lengths (IL = 15, 45, 180). The developed models were tested for runoff forecasting using three basins (with different characteristics) from the Catchment Attributes and MEteorology for Large-sample Studies (CAMELS) dataset. The models were compared using deterministic (e.g., the Kling-Gupta efficiency [KGE] metric) and probabilistic (e.g., reliability) statistical metrics. While the models showed high variability in performance across the three basins (KGE = 0.308-0.979 for the q = 0.5 models), very high accuracy (up to KGE = 0.979) was achieved for one of the basins with high snowmelt. The ED-NLW model was found to generally outperform the other models. Although the LSTM-DN model had the highest median KGE (0.434 across all configurations), the ED and ED-NLW models had higher reliability than LSTM-DN (90% and 91%, respectively, considering a 90% confidence level). Models coupled with NLW performed superior to those that used LW. All ED models had high reliability despite two of the basins achieving median KGE values of similar to 0.390, highlighting that quantile-based models can generate reliable forecast intervals even when the KGE of the median forecast (q = 0.5) is low. An additional experiment generated synthetic precipitation forecasts with varying degrees

关键词： encoder-decoder Deep learning LSTM Wavelet decomposition Runoff forecasting Hydrological forecasting

来源：评论

学校读者我要写书评

暂无评论

The trade-off between topology and content in community detection: An adaptive encoder-decoder-based NMF approach

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 209卷

作者： Zhao, Zhili Ke, Zhengyou Gou, Zhuoyue Guo, Hao Jiang, Kunyuan Zhang, Ruisheng Lanzhou Univ Sch Informat Sci & Engn Lanzhou 730000 Peoples R China

Community detection is an important research field of complex network analysis and focuses on the study of networks' aggregation behaviours. Different from traditional methods that only consider network structural topology, many efforts have been put into combining network structural topology with node content attributes to achieve better community detection performance. However, it is critical to make an appropriate trade-off between structural topology and node content. In this paper, we propose an adaptive trade-off approach, called ANMF, which not only considers both structural topology and node content, but also provides a flexible parameter to balance their contribution. Compared with other related approaches, ANMF is a kind of non-negative matrix factorization (NMF)-based community detection method, but it imposes more constraints on the network reconstruction. More precisely, ANMF simultaneously employs a decoder that reconstructs a network from its community membership space and an encoder that transforms the network into the community membership space. Moreover, compared with the most related state-of-the-art effort adaptive semantic community detection (ASCD), which considers the topology part always has more contribution if there is a mismatch, ANMF considers the mismatch in two different situations, i.e., the topology part contributes more than the node content part and the node content part contributes more than the topology part. Based on the intensive evaluation on both real and artificial networks, ANMF provides higher normalized mutual information (NMI) values of 4.95%similar to 126.41% than the models without considering node content information on 13 out of 14 experimental networks. ANMF also presents higher NMI values of 7.38%similar to 201.01% than ASCD on 13 out of 14 experimental networks. Moreover, ANMF shows good convergence performance, and it can converge after 100 iterations on all of the networks. ANMF also provides stability alike to s

关键词： Non-negative matrix factorization Community detection encoder-decoder Network topology Node attributes

来源：评论

学校读者我要写书评

暂无评论

Efficient MRI Brain Tumor Segmentation Using Multi-resolution encoder-decoder Networks 1

引用

6th International MICCAI Brain-Lesion Workshop (BrainLes)

作者： Soltaninejad, Mohammadreza Pridmore, Tony Pound, Michael Univ Nottingham Sch Comp Sci Comp Vis Lab Nottingham England

ISBN: (数字)9783030720872

ISBN: (纸本)9783030720865;9783030720872

In this paper, we propose an automated three dimensional (3D) deep learning approach for the segmentation of gliomas in pre-operative brain MRI scans. We introduce a state-of-the-art multi-resolution architecture based on encoder-decoder which comprise of separate branches to incorporate local high-resolution image features and wider low-resolution contextual information. We also used a unified multi-task loss function to provide end-to-end segmentation training. For the task of survival prediction, we propose a regression algorithm based on random forests to predict the survival days for the patients. Our proposed network is fully automated and designed to take input as patches that can work on input images of any arbitrary size. We trained our proposed network on the BraTS 2020 challenge dataset that consists of 369 training cases, and then validated on 125 unseen validation datasets, and tested on 166 unseen cases from the testing dataset using a blind testing approach. The quantitative and qualitative results demonstrate that our proposed network provides efficient segmentation of brain tumors. The mean Dice overlap measures for automatic brain tumor segmentation of the validation dataset against ground truth are 0.87, 0.80, and 0.66 for the whole tumor, core, and enhancing tumor, respectively. The corresponding results for the testing dataset are 0.78, 0.70, and 0.66, respectively. The accuracy measures of the proposed model for the survival prediction tasks are 0.45 and 0.505 for the validation and testing datasets, respectively.

关键词： Convolutional neural network encoder-decoder Deep learning MRI Brain tumor segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：