Query：
学者姓名：孟德宇
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
As common weather, rain streaks adversely degrade the image quality and tend to negatively affect the performance of outdoor computer vision systems. Hence, removing rains from an image has become an important issue in the field. To handle such an ill-posed single image deraining task, in this article, we specifically build a novel deep architecture, called rain convolutional dictionary network (RCDNet), which embeds the intrinsic priors of rain streaks and has clear interpretability. In specific, we first establish a rain convolutional dictionary (RCD) model for representing rain streaks and utilize the proximal gradient descent technique to design an iterative algorithm only containing simple operators for solving the model. By unfolding it, we then build the RCDNet in which every network module has clear physical meanings and corresponds to each operation involved in the algorithm. This good interpretability greatly facilitates an easy visualization and analysis of what happens inside the network and why it works well in the inference process. Moreover, taking into account the domain gap issue in real scenarios, we further design a novel dynamic RCDNet, where the rain kernels can be dynamically inferred corresponding to input rainy images and then help shrink the space for rain layer estimation with few rain maps, so as to ensure a fine generalization performance in the inconsistent scenarios of rain types between training and testing data. By end-to-end training such an interpretable network, all involved rain kernels and proximal operators can be automatically extracted, faithfully characterizing the features of both rain and clean background layers and, thus, naturally leading to better deraining performance. Comprehensive experiments implemented on a series of representative synthetic and real datasets substantiate the superiority of our method, especially on its well generality to diverse testing scenarios and good interpretability for all its modules, compared with state-of-the-art single image derainers both visually and quantitatively.
Keyword ：
Dictionary learning generalization performance interpretable deep learning (DL) single image rain removal
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Hong , Xie, Qi , Zhao, Qian et al. RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining [J]. | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2023 . |
| MLA | Wang, Hong et al. "RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining" . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023) . |
| APA | Wang, Hong , Xie, Qi , Zhao, Qian , Li, Yuexiang , Liang, Yong , Zheng, Yefeng et al. RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2023 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
During the computed tomography (CT) imaging process, metallic implants within patients often cause harmful artifacts, which adversely degrade the visual quality of reconstructed CT images and negatively affect the subsequent clinical diagnosis. For the metal artifact reduction (MAR) task, current deep learning based methods have achieved promising performance. However, most of them share two main common limitations: (1) the CT physical imaging geometry constraint is not comprehensively incorporated into deep network structures; (2) the entire framework has weak interpretability for the specific MAR task; hence, the role of each network module is difficult to be evaluated. To alleviate these issues, in the paper, we construct a novel deep unfolding dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. Concretely, we derive a joint spatial and Radon domain reconstruction model and propose an optimization algorithm with only simple operators for solving it. By unfolding the iterative steps involved in the proposed algorithm into the corresponding network modules, we easily build the InDuDoNet+ with clear interpretability. Furthermore, we analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance. Comprehensive experiments on synthesized data and clinical data substantiate the superiority of the proposed methods as well as the superior generalization performance beyond the current state-of-the-art (SOTA) MAR methods. Code is available at https://github.com/hongwang01/InDuDoNet_plus.
Keyword ：
CT imaging geometry Generalization ability Metal artifact reduction Physical interpretability
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Hong , Li, Yuexiang , Zhang, Haimiao et al. InDuDoNet plus : A deep unfolding dual domain network for metal artifact reduction in CT images [J]. | MEDICAL IMAGE ANALYSIS , 2023 , 85 . |
| MLA | Wang, Hong et al. "InDuDoNet plus : A deep unfolding dual domain network for metal artifact reduction in CT images" . | MEDICAL IMAGE ANALYSIS 85 (2023) . |
| APA | Wang, Hong , Li, Yuexiang , Zhang, Haimiao , Meng, Deyu , Zheng, Yefeng . InDuDoNet plus : A deep unfolding dual domain network for metal artifact reduction in CT images . | MEDICAL IMAGE ANALYSIS , 2023 , 85 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Existing convolutional neural network (CNN)-based and vision Transformer (ViT)-based image restora-tion methods are usually explored in the spatial domain. However, we employ Fourier analysis to show that these spatial domain models cannot perceive the entire frequency spectrum of images, i.e., mainly focus on either high-frequency (CNN-based models) or low-frequency components (ViT-based models). This intrinsic limitation results in the partial missing of semantic information and the appearance of artifacts. To address this limitation, we propose a novel uncertainty-guided hierarchical frequency domain Transformer named HFDT to effectively learn both high and low-frequency information while perceiving local and global features. Specifically, to aggregate semantic information from various fre-quency levels, we propose a dual-domain feature interaction mechanism, in which the global frequency information and local spatial features are extracted by corresponding branches. The frequency domain branch adopts the Fast Fourier Transform (FFT) to convert the features from the spatial domain to the frequency domain, where the global low and high-frequency components are learned with Log -linear complexity. Complementarily, an efficient convolution group is employed in the spatial domain branch to capture local high-frequency details. Moreover, we introduce an uncertainty degradation -guided strategy to efficiently represent degraded prior information, rather than simply distinguishing degraded/non-degraded regions in binary form. Our approach achieves competitive results in several degraded scenarios, including rain streaks, raindrops, motion blur, and defocus blur.(c) 2023 Elsevier B.V. All rights reserved.
Keyword ：
Frequency-domain Transformer Image restoration Log-linear complexity Uncertainty-guided
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Shao, Mingwen , Qiao, Yuanjian , Meng, Deyu et al. Uncertainty-guided hierarchical frequency domain Transformer for image restoration [J]. | KNOWLEDGE-BASED SYSTEMS , 2023 , 263 . |
| MLA | Shao, Mingwen et al. "Uncertainty-guided hierarchical frequency domain Transformer for image restoration" . | KNOWLEDGE-BASED SYSTEMS 263 (2023) . |
| APA | Shao, Mingwen , Qiao, Yuanjian , Meng, Deyu , Zuo, Wangmeng . Uncertainty-guided hierarchical frequency domain Transformer for image restoration . | KNOWLEDGE-BASED SYSTEMS , 2023 , 263 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Visual Question Answering (VQA) has attracted extensive research focus recently. Along with the ever-increasing data scale and model complexity, the enormous training cost has become an emerging challenge for VQA. In this article, we show such a massive training cost is indeed plague. In contrast, a fine-grained design of the learning paradigm can be extremely beneficial in terms of both training efficiency and model accuracy. In particular, we argue that there exist two essential and unexplored issues in the existing VQA training paradigm that randomly samples data in each epoch, namely, the "difficulty diversity" and the "label redundancy". Concretely, "difficulty diversity" refers to the varying difficulty levels of different question types, while "label redundancy" refers to the redundant and noisy labels contained in individual question type. To tackle these two issues, in this article we propose a fine-grained VQA learning paradigm with an actor-critic based learning agent, termed FG-A1C. Instead of using all training data from scratch, FG-A1C includes a learning agent that adaptively and intelligently schedules the most difficult question types in each training epoch. Subsequently, two curriculum learning based schemes are further designed to identify the most useful data to be learned within each inidividual question type. We conduct extensive experiments on the VQA2.0 and VQA-CP v2 datasets, which demonstrate the significant benefits of our approach. For instance, on VQA-CP v2, with less than 75 percent of the training data, our learning paradigms can help the model achieves better performance than using the whole dataset. Meanwhile, we also shows the effectivenesss of our method in guiding data labeling. Finally, the proposed paradigm can be seamlessly integrated with any cutting-edge VQA models, without modifying their structures.
Keyword ：
Data models Feature extraction Fine-grained learning Knowledge discovery Redundancy Training Training data Visualization visual question answering
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhou, Yiyi , Ji, Rongrong , Sun, Xiaoshuai et al. Plenty is Plague: Fine-Grained Learning for Visual Question Answering [J]. | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2022 , 44 (2) : 697-709 . |
| MLA | Zhou, Yiyi et al. "Plenty is Plague: Fine-Grained Learning for Visual Question Answering" . | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 44 . 2 (2022) : 697-709 . |
| APA | Zhou, Yiyi , Ji, Rongrong , Sun, Xiaoshuai , Su, Jinsong , Meng, Deyu , Gao, Yue et al. Plenty is Plague: Fine-Grained Learning for Visual Question Answering . | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2022 , 44 (2) , 697-709 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Action detection plays an important role in video understanding and attracts considerable attention in the last decade. However, current action detection methods are mainly based on visible videos, and few of them consider scenes with low-light, where actions are difficult to be detected by existing methods, or even by human eyes. Compared with visible videos, infrared videos are more suitable for the dark environment and resistant to background clutter. In this paper, we investigate the temporal action detection problem in the dark by using infrared videos, which is, to the best of our knowledge, the first attempt in the action detection community. Our model takes the whole video as input, a Flow Estimation Network (FEN) is employed to generate the optical flow for infrared data, and it is optimized with the whole network to obtain action-related motion representations. After feature extraction, the infrared stream and flow stream are fed into a Selective Cross-stream Attention (SCA) module to narrow the performance gap between infrared and visible videos. The SCA emphasizes informative snippets and focuses on the more discriminative stream automatically. Then we adopt a snippet-level classifier to obtain action scores for all snippets and link continuous snippets into final detections. All these modules are trained in an end-to-end manner. We collect an Infrared action Detection (InfDet) dataset obtained in the dark and conduct extensive experiments to verify the effectiveness of the proposed method. Experimental results show that our proposed method surpasses state-of-the-art temporal action detection methods designed for visible videos, and it also achieves the best performance compared with other infrared action recognition methods on both InfAR and Infrared-Visible datasets.
Keyword ：
Feature extraction Image recognition Infrared video Optical imaging Proposals selective cross-stream attention Streaming media Task analysis temporal action detection Three-dimensional displays
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Xu , Gao, Chenqiang , Li, Chaoyu et al. Infrared Action Detection in the Dark via Cross-Stream Attention Mechanism [J]. | IEEE TRANSACTIONS ON MULTIMEDIA , 2022 , 24 : 288-300 . |
| MLA | Chen, Xu et al. "Infrared Action Detection in the Dark via Cross-Stream Attention Mechanism" . | IEEE TRANSACTIONS ON MULTIMEDIA 24 (2022) : 288-300 . |
| APA | Chen, Xu , Gao, Chenqiang , Li, Chaoyu , Yang, Yi , Meng, Deyu . Infrared Action Detection in the Dark via Cross-Stream Attention Mechanism . | IEEE TRANSACTIONS ON MULTIMEDIA , 2022 , 24 , 288-300 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
In this paper, we propose an infinite-dimensional version of the Stein variational gradient descent (iSVGD) method for solving Bayesian inverse problems. The method can generate approximate samples from posteriors efficiently. Based on the concepts of operator-valued kernels and vector-valued reproducing kernel Hilbert spaces, a rigorous definition is given for the infinite-dimensional objects, e.g., the Stein operator, which are proved to be the limit of finite-dimensional ones. Moreover, a more efficient iSVGD with preconditioning operators is constructed by generalizing the change of variables formula and introducing a regularity parameter. The proposed algorithms are applied to an inverse problem of the steady state Darcy flow equation. Numerical results confirm our theoretical findings and demonstrate the potential applications of the proposed approach in the posterior sampling of large-scale nonlinear statistical inverse problems.
Keyword ：
Bayes? method machine learning statistical inverse problems Stein variational gradient descent variational inference method
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jia, Junxiong , LI, Peijun , Meng, Deyu . STEIN VARIATIONAL GRADIENT DESCENT ON INFINITE-DIMENSIONAL SPACE AND APPLICATIONS TO STATISTICAL INVERSE PROBLEMS [J]. | SIAM JOURNAL ON NUMERICAL ANALYSIS , 2022 , 60 (4) : 2225-2252 . |
| MLA | Jia, Junxiong et al. "STEIN VARIATIONAL GRADIENT DESCENT ON INFINITE-DIMENSIONAL SPACE AND APPLICATIONS TO STATISTICAL INVERSE PROBLEMS" . | SIAM JOURNAL ON NUMERICAL ANALYSIS 60 . 4 (2022) : 2225-2252 . |
| APA | Jia, Junxiong , LI, Peijun , Meng, Deyu . STEIN VARIATIONAL GRADIENT DESCENT ON INFINITE-DIMENSIONAL SPACE AND APPLICATIONS TO STATISTICAL INVERSE PROBLEMS . | SIAM JOURNAL ON NUMERICAL ANALYSIS , 2022 , 60 (4) , 2225-2252 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Precise segmentation of teeth from intra-oral scanner images is an essential task in computer-aided orthodontic surgical planning. The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i.e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation. However, since different raw attributes reveal completely different geometric information, the naive concatenation of different raw attributes at the (low-level) input stage may bring unnecessary confusion in describing and differentiating between mesh cells, thus hampering the learning of high-level geometric representations for the segmentation task. To address this issue, we design a two-stream graph convolutional network (i.e., TSGCN), which can effectively handle inter-view confusion between different raw attributes to more effectively fuse their complementary information and learn discriminative multi-view geometric representations. Specifically, our TSGCN adopts two input-specific graph-learning streams to extract complementary high-level geometric representations from coordinates and normal vectors, respectively. Then, these single-view representations are further fused by a self-attention module to adaptively balance the contributions of different views in learning more discriminative multi-view representations for accurate and fully automatic tooth segmentation. We have evaluated our TSGCN on a real-patient dataset of dental (mesh) models acquired by 3D intraoral scanners. Experimental results show that our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
Keyword ：
Dentistry Feature extraction graph convolutional network Image segmentation Intra-oral scanner image segmentation Shape Task analysis Teeth Three-dimensional displays
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhao, Yue , Zhang, Lingming , Liu, Yang et al. Two-Stream Graph Convolutional Network for Intra-Oral Scanner Image Segmentation [J]. | IEEE TRANSACTIONS ON MEDICAL IMAGING , 2022 , 41 (4) : 826-835 . |
| MLA | Zhao, Yue et al. "Two-Stream Graph Convolutional Network for Intra-Oral Scanner Image Segmentation" . | IEEE TRANSACTIONS ON MEDICAL IMAGING 41 . 4 (2022) : 826-835 . |
| APA | Zhao, Yue , Zhang, Lingming , Liu, Yang , Meng, Deyu , Cui, Zhiming , Gao, Chenqiang et al. Two-Stream Graph Convolutional Network for Intra-Oral Scanner Image Segmentation . | IEEE TRANSACTIONS ON MEDICAL IMAGING , 2022 , 41 (4) , 826-835 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Although current deep learning-based methods have gained promising performance in the blind single image super-resolution (SISR) task, most of them mainly focus on heuristically constructing diverse network architectures and put less emphasis on the explicit embedding of the physical generation mechanism between blur kernels and highresolution (HR) images. To alleviate this issue, we propose a modeldriven deep neural network, called KXNet, for blind SISR. Specifically, to solve the classical SISR model, we propose a simple-yet-effective iterative algorithm. Then by unfolding the involved iterative steps into the corresponding network module, we naturally construct the KXNet. The main specificity of the proposed KXNet is that the entire learning process is fully and explicitly integrated with the inherent physical mechanism underlying this SISR task. Thus, the learned blur kernel has clear physical patterns and the mutually iterative process between blur kernel and HR image can soundly guide the KXNet to be evolved in the right direction. Extensive experiments on synthetic and real data finely demonstrate the superior accuracy and generality of our method beyond the current representative state-of-the-art blind SISR methods. Code is available at: https://github.com/jiahong- fu/KXNet.
Keyword ：
Blind single image super-resolution Kernel estimation Model-driven Mutual learning Physical generation mechanism
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fu, Jiahong , Wang, Hong , Xie, Qi et al. KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution [J]. | COMPUTER VISION, ECCV 2022, PT XIX , 2022 , 13679 : 235-253 . |
| MLA | Fu, Jiahong et al. "KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution" . | COMPUTER VISION, ECCV 2022, PT XIX 13679 (2022) : 235-253 . |
| APA | Fu, Jiahong , Wang, Hong , Xie, Qi , Zhao, Qian , Meng, Deyu , Xu, Zongben . KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution . | COMPUTER VISION, ECCV 2022, PT XIX , 2022 , 13679 , 235-253 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Multispectral and hyperspectral image fusion (MS/HS fusion) aims to fuse a high-resolution multispectral (HrMS) and a low-resolution hyperspectral (LrHS) images to generate a high-resolution hyperspectral (HrHS) image, which has become one of the most commonly addressed problems for hyperspectral image processing. In this paper, we specifically designed a network architecture for the MS/HS fusion task, called MHF-net, which not only contains clear interpretability, but also reasonably embeds the well studied linear mapping that links the HrHS image to HrMS and LrHS images. In particular, we first construct an MS/HS fusion model which merges the generalization models of low-resolution images and the low-rankness prior knowledge of HrHS image into a concise formulation, and then we build the proposed network by unfolding the proximal gradient algorithm for solving the proposed model. As a result of the careful design for the model and algorithm, all the fundamental modules in MHF-net have clear physical meanings and are thus easily interpretable. This not only greatly facilitates an easy intuitive observation and analysis on what happens inside the network, but also leads to its good generalization capability. Based on the architecture of MHF-net, we further design two deep learning regimes for two general cases in practice: consistent MHF-net and blind MHF-net. The former is suitable in the case that spectral and spatial responses of training and testing data are consistent, just as considered in most of the pervious general supervised MS/HS fusion researches. The latter ensures a good generalization in mismatch cases of spectral and spatial responses in training and testing data, and even across different sensors, which is generally considered to be a challenging issue for general supervised MS/HS fusion methods. Experimental results on simulated and real data substantiate the superiority of our method both visually and quantitatively as compared with state-of-the-art methods along this line of research.
Keyword ：
generalization Hyperspectral imaging image restoration interpretable deep learning Multispectral and hyperspectral image fusion Network architecture Sensors Task analysis Testing Training
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xie, Qi , Zhou, Minghao , Zhao, Qian et al. MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion [J]. | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2022 , 44 (3) : 1457-1473 . |
| MLA | Xie, Qi et al. "MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion" . | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 44 . 3 (2022) : 1457-1473 . |
| APA | Xie, Qi , Zhou, Minghao , Zhao, Qian , Xu, Zongben , Meng, Deyu . MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion . | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2022 , 44 (3) , 1457-1473 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Although deep neural networks (DNNs) have been widely applied to hyperspectral image (HSI) denoising, most DNN-based HSI denoising methods are designed by stacking convolution layer, which can only model and reason local relations, and thus ignore the global contextual information. To address this issue, we propose a deep spatial-spectral global reasoning network to consider both the local and global information for HSI noise removal. Specifically, two novel modules are proposed to model and reason global relational information. The first one aims to model global spatial relations between pixels in feature maps, and the second one models the global relations across the channels. Compared to traditional convolution operations, the two proposed modules enable the network to extract representations from new dimensions. For the HSI denoising task, the two modules, as well as the densely connected structures, are embedded into the U-Net architecture. Thus, the new-designed global reasoning network can help tackle complex noise by exploiting multiple representations, e.g., hierarchical local feature, global spatial coherence, cross-channel correlation, and multi-scale abstract representation. Experiments on both synthetic and real HSI data demonstrate that our proposed network can obtain comparable or even better denoising results than other state-of-the-art methods.
Keyword ：
Cognition Correlation Decoding Deep neural network (DNN) Feature extraction global channel module (GCM) global spatial module (GSM) GSM hyperspectral image (HSI) denoising Noise reduction Task analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cao, Xiangyong , Fu, Xueyang , Xu, Chen et al. Deep Spatial-Spectral Global Reasoning Network for Hyperspectral Image Denoising [J]. | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2022 , 60 . |
| MLA | Cao, Xiangyong et al. "Deep Spatial-Spectral Global Reasoning Network for Hyperspectral Image Denoising" . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 60 (2022) . |
| APA | Cao, Xiangyong , Fu, Xueyang , Xu, Chen , Meng, Deyu . Deep Spatial-Spectral Global Reasoning Network for Hyperspectral Image Denoising . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2022 , 60 . |
| Export to | NoteExpress RIS BibTex |
Export
| Results： |
Selected to |
| Format： |
