检索结果-内蒙古大学图书馆

Multi-Level Adaptive Attention Fusion Network for Infrared and Visible Image Fusion

IEEE SIGNAL pROCESSING LETTERS 2025年 32卷 366-370页

作者： Hu, Ziming Kong, Quan Liao, Qing Wuhan Inst Technol Hubei Key Lab Opt Informat & Pattern Recognit Wuhan 430205 Peoples R China Wuhan Inst Technol Hubei Key Lab Opt Informat & Pattern Recognit Wuhan 430205 Peoples R China Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan 430205 Peoples R China

Infrared and visible image fusion involves integrating complementary or critical information extracted from different source images into one image. Due to the significant differences between the two modality features and those across different scales, traditional fusion strategies, such as addition or concatenation, often result in information redundancy or the degradation of crucial information. This letter proposes a multi-level adaptive attention fusion network to adaptively fuse features extracted from different sources. Specifically, we introduced an Adaptive Scale Attention Fusion (ASAF) module that uses a soft selection mechanism to assess the relative importance of different modality features at the same scale and assign corresponding fusion weights. Additionally, a guided upsampling layer is utilized to integrate shallow and deep feature information at different scales in the multi-scale structure. Qualitative and quantitative results on public datasets validate the superior performance of our approach in both visual effects and quantitative metrics.

关键词： Feature extraction Convolution Fuses Image fusion Context modeling Adaptation models Adaptive systems Transforms Optical signal processing Optical imaging Adaptive fusion strategy image fusion infrared image upsampling

来源：评论

学校读者我要写书评

暂无评论

Deep progressive Asymmetric Quantization Based on Causal Intervention for Fine-Grained Image Retrieval

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 1306-1318页

作者： Ma, Lei Hong, Hanyu Meng, Fanman Wu, Qingbo Wu, Jinmeng Wuhan Inst Technol Sch Elect & Informat Engn Hubei Key Lab Opt Informat & Pattern Recognit Wuhan 430079 Peoples R China Univ Elect Sci & Technol China Sch Elect Engn Intelligent Visual Informat Proc & Commun Lab Chengdu 610056 Peoples R China

In the field of computer vision, fine-grained image retrieval is an extremely challenging task due to the inherently subtle intra-class object variations. In addition, the high-dimensional real-valued features extracted from large-scale fine-grained image datasets slow the retrieval speed and increase the storage cost. To solve above issues, existing fine-grained image retrieval methods mainly focus on finding more discriminative local regions for generating discriminative and compact hash codes, which achieve limited fine-grained image retrieval performance due to the large quantization errors and the confounding granularities and context of discriminative parts, i.e., the correct recognition of fine-grained objects mainly attribute to the discriminative parts and their context. To learn robust causal features and reduce the quantization errors, we propose a deep progressive asymmetric quantization (DpAQ) method based on causal intervention to learn compact and robust descriptions for fine-grained image retrieval task. Specifically, we introduce a structural causal model to learn robust casual features via causal intervention for fine-grained visual recognition. Subsequently, we design a progressive asymmetric quantization layer in the feature embedding space, which can preserve the semantic information and reduce the quantization errors sufficiently. Finally, we incorporate both the fine-grained image classification and retrieval tasks into an end-to-end deep learning architecture for generating robust and compact descriptions. Experimental results on several fine-grained image retrieval datasets demonstrate that the proposed DpAQ method performs the best for fine-grained image retrieval task and surpasses the state-of-the art fine-grained hashing methods by a large margin.

关键词： Quantization (signal) Image retrieval Semantics Task analysis Visualization Vector quantization Training Causal intervention deep progressive asymmetric quantization fine-grained image retrieval structural causal model

来源：评论

学校读者我要写书评

暂无评论

Logit Variated product Quantization Based on parts Interaction and Metric Learning With Knowledge Distillation for Fine-Grained Image Retrieval

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 10406-10419页

作者： Ma, Lei Luo, Xin Hong, Hanyu Meng, Fanman Wu, Qingbo Wuhan Inst Technol Sch Elect & Informat Engn Hubei Key Lab Opt Informat & Pattern Recognit Hubei 430079 Peoples R China Univ Elect Sci & Technol China Sch Elect Engn Intelligent Visual Informat Proc & Commun Lab IVIP Chengdu 611731 Peoples R China

Image retrieval with fine-grained categories is an extremely challenging task due to the high intraclass variance and low interclass variance. Most previous works have focused on localizing discriminative image regions in isolation, but have rarely exploited correlations across the different discriminative regions to alleviate intraclass differences. In addition, the intraclass compactness of embedding features is ensured by extra regularization terms that only exist during the training phase, which appear to generalize less well in the inference phase. Finally, the information granularity of the distance measure should distinguish subtle visual differences and the correlation between the embedding features and the quantized features should be maximized sufficiently. To address the above issues, we propose a logit variated product quantization method based on part interaction and metric learning with knowledge distillation for fine-grained image retrieval. Specifically, we introduce a causal context module into the deep navigator to generate discriminative regions and utilize a channelwise cross-part fusion transformer to model the part correlations while alleviating intraclass differences. Subsequently, we design a logit variation module based on a weighted sum scheme to further reduce the intraclass variance of the embedding features directly and enhance the learning power of the quantization model. Finally, we propose a novel product quantization loss based on metric learning and knowledge distillation to enhance the correlation between the embedding features and the quantized features and allow the quantization features to learn more knowledge from the embedding features. The experimental results on several fine-grained datasets demonstrate that the proposed method is superior to state-of-the-art fine-grained image retrieval methods.

关键词： Image retrieval Quantization (signal) Feature extraction Visualization Correlation Measurement Task analysis Logit variation parts interaction product quantization metric learning knowledge distillation fine-grained image retrieval

来源：评论

学校读者我要写书评

暂无评论

Dynamic behavior and modulation instability for a generalized nonlinear Schrödinger equation with nonlocal nonlinearity

引用

pHYSICA SCRIpTA 2025年第1期100卷

作者： Zhang, Kun Cao, Jiangping Lyu, Jingjing Chengdu Univ Coll Comp Sci Chengdu 610106 Peoples R China Chengdu Univ Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu 610106 Peoples R China Natl Inst Measurement & Testing Technol Chengdu 610021 Peoples R China

This paper focus on the generalized nonlinear Schr & ouml;dinger equation with triple refractive index and nonlocal nonlinearity, which is used to describe the evolution state of optical solitons in fiber optic propagation. Firstly, the complex exponential traveling wave transformation and substitution method are utilized to convert the equation into two-dimensional planar dynamic system, and then by phase portrait the developmental patterns of solutions are qualitatively analyzing. Meanwhile, the evolution of solutions under different disturbances in the system is discussed. Qualitative analysis of the system are displayed through poincar & eacute;section and sensitivity analysis. Finally, the instability of the system is modulated by using linear stability analysis method, and the corresponding conditions for steady-state solutions and the gain spectrum function are obtained.

关键词： nonlocal nonlinearity chaotic behavior dispersion effect modulation instability

来源：评论

学校读者我要写书评

暂无评论

CASpFuse: An Infrared and Visible Image Fusion Method Based on Dual-Cycle Crosswise Awareness and Global Structure-Tensor preservation

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Li, Xuan Chen, Rongfu Wang, Jie Chen, Weiwei Zhou, Huabing Ma, Jiayi Wuhan Inst Technol Hubei Key Lab Opt Informat & Pattern Recognit Wuhan 430205 Peoples R China Fiberhome Telecommun Technol CompanyLtd Wuhan 430073 Peoples R China Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan 430200 Peoples R China Wuhan Univ Elect Informat Sch Wuhan 430072 Peoples R China

The inconsistency in the feature spaces of cross-modality images makes it challenging to adaptively fuse images of different modalities. The fusion rules inevitably have global or local proneness toward one modality. To address the challenge, this article proposes a novel fusion method based on dual-cycle crosswise awareness and global structure-tensor preservation (CASpFuse), which is a modal transition network and contrives images taking part in the fusion operation to have similar feature spaces. First, a dual-cycle modality transition (DMT) network is proposed. Under the guidance of cross-aware-based adversarial learning and the constraints of edge prior, it allows the generated images better inherit the specialties of original images on the basis of pursuing the modal transition. Second, a set of global structure-tensor preserving (STp) models and STp-aware loss are designed to enhance the capabilities of the network in structural preservation and modal consistency perception. STp-aware loss, collaborate with cycle-consistency loss and cross-aware loss, enable our network to effectively supervise the generation of high-quality pseudo images and to eliminate the adverse artifacts and structural degradation. Third, we devise a progressively adaptive fusion (pAF) network, which sequentially generates pairwise images with unified modalities and fine-tunes their structures to overcome the challenge of effective aggregation of different modal attributes. Extensive comparative experiments demonstrate that our CASpFuse outperforms state-of-the-art fusion methods in adequately expressing the advantageous complementary information of different modalities. The source code is available at https://***/xbsj-cool/CASpFuse.

关键词： Deep learning image fusion modality transition structure awareness Deep learning image fusion modality transition structure awareness

来源：评论

学校读者我要写书评

暂无评论

GMAlignNet: multi-scale lightweight brain tumor image segmentation with enhanced semantic information consistency

引用

pHYSICS IN MEDICINE AND BIOLOGY 2024年第11期69卷 115033-115033页

作者： Song, Jianli Lu, Xiaoqi Gu, Yu Inner Mongolia Univ Sci & Technol Sch Digital & Intelligent Ind Inner Mongolia Key Lab Pattern Recognit & Intellig Baotou Peoples R China Inner Mongolia Univ Technol Sch Informat Engn Hohhot 010051 Peoples R China

Although the U-shaped architecture, represented by UNet, has become a major network model for brain tumor segmentation, the repeated convolution and sampling operations can easily lead to the loss of crucial information. Additionally, directly fusing features from different levels without distinction can easily result in feature misalignment, affecting segmentation accuracy. On the other hand, traditional convolutional blocks used for feature extraction cannot capture the abundant multi-scale information present in brain tumor images. This paper proposes a multi-scale feature-aligned segmentation model called GMAlignNet that fully utilizes Ghost convolution to solve these problems. Ghost hierarchical decoupled fusion unit and Ghost hierarchical decoupled unit are used instead of standard convolutions in the encoding and decoding paths. This transformation replaces the holistic learning of volume structures by traditional convolutional blocks with multi-level learning on a specific view, facilitating the acquisition of abundant multi-scale contextual information through low-cost operations. Furthermore, a feature alignment unit is proposed that can utilize semantic information flow to guide the recovery of upsampled features. It performs pixel-level semantic information correction on misaligned features due to feature fusion. The proposed method is also employed to optimize three classic networks, namely DMFNet, HDCNet, and 3D UNet, demonstrating its effectiveness in automatic brain tumor segmentation. The proposed network model was applied to the BraTS 2018 dataset, and the results indicate that the proposed GMAlignNet achieved Dice coefficients of 81.65%, 90.07%, and 85.16% for enhancing tumor, whole tumor, and tumor core segmentation, respectively. Moreover, with only 0.29 M parameters and 26.88G FLOps, it demonstrates better potential in terms of computational efficiency and possesses the advantages of lightweight. Extensive experiments on the BraTS 2018, BraTS 2

关键词： brain tumor image segmentation lightweight feature alignment U-Net multi-scale

来源：评论

学校读者我要写书评

暂无评论

Bifurcation soliton solutions, M-lump, breather waves, and interaction solutions for (3+1)-dimensional p-type equation

引用

CHAOS SOLITONS & FRACTALS 2025年 192卷

作者： Wang, Tianlin Tian, Lin Ma, Zhimin Yang, Zhuodong Han, Hongwei Chengdu Univ Technol Engn & Tech Coll Leshan 614000 Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu Peoples R China Chengdu Univ Technol Geomath Key Lab Sichuan Prov Chengdu 610068 Peoples R China

In this paper, we employ the Bell polynomial to derive the Hirota bilinear form and obtain multi-soliton solutions using the Hirota bilinear method. Based on the multi-soliton solutions, we derive the resonant Ytype soliton, the heterotypic soliton, and the X-type soliton by setting the partial dispersion coefficient to zero. Additionally, the M-lump wave solutions are constructed using the long-wave limit method, and their various characteristics, as well as the collision phenomena of the 2-lump and 3-lump solutions, are analyzed. Breather waves are derived as well, using the complex conjugation method. Finally, we study the interaction solutions and observe that their collision is elastic, demonstrated them through figures. These solutions have broad applications in nonlinear science, enhancing our understanding of related physical phenomena and contributing to an in-depth investigation of complex nonlinear problems.

关键词： Y-type soliton X-type soliton M-lump waves Breather waves Heterotypic soliton Interaction solutions Long-wave limit method

来源：评论

学校读者我要写书评

暂无评论

practically Unbiased pairwise Loss for Recommendation With Implicit Feedback

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2025年第4期47卷 2460-2474页

作者： Cao, Tianwei Xu, Qianqian Yang, Zhiyong Ma, Zhanyu Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Beijing Univ Posts & Telecommun Sch Artificial Intelligence Pattern Recognit & Intelligent Syst Lab Beijing 100876 Peoples R China Chinese Acad Sci Key Lab Intelligent Informat Proc Inst Comp Technol Beijing 100190 Peoples R China Beijing Univ Posts & Telecommun Sch Artificial Intelligence Pattern Recognit & Intelligent Syst Lab Beijing Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management BDKM Beijing 101408 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

Recommender systems have been widely employed on various online platforms to improve user experience. In these systems, recommendation models are often learned from the users' historical behaviors that are automatically collected. Notably, recommender systems differ slightly from ordinary supervised learning tasks. In recommender systems, there is an exposure mechanism that decides which items could be presented to each specific user, which breaks the i.i.d assumption of supervised learning and brings biases into the recommendation models. In this paper, we focus on unbiased ranking loss weighted by inversed propensity scores (IpS), which are widely used in recommendations with implicit feedback labels. More specifically, we first highlight the fact that there is a gap between theory and practice in IpS-weighted unbiased loss. The existing pairwise loss could be theoretically unbiased by adopting an IpS weighting scheme. Unfortunately, the propensity scores are hard to estimate due to the inaccessibility of each user-item pair's true exposure status. In practical scenarios, we can only approximate the propensity scores. In this way, the theoretically unbiased loss would be still practically biased. To solve this problem, we first construct a theoretical framework to obtain a generalization upper bound of the current theoretically unbiased loss. The bound illustrates that we can ensure the theoretically unbiased loss's generalization ability if we lower its implementation loss and practical bias at the same time. To that aim, we suggest treating feedback label Y-ui as a noisy proxy for exposure result for O-ui each user-item pair (u,i). Here we assume the noise rate meets the condition that (p) over cap O-ui=1, Y-ui not equal O-ui) < 1/2. According to our analysis, this is a mild assumption that can be satisfied by many real-world applications. Based on this, we could train an accurate propensity model directly by leveraging a noise-resistant loss function. Then we c

关键词： Estimation Imputation Training data Ip networks Accuracy Supervised learning Recommender systems Noise Data models Computer science Recommender system collaborative filtering debias noise-robust learning pairwise ranking loss

来源：评论

学校读者我要写书评

暂无评论

DSAFusion: Detail-semantic-aware network for infrared and low-light visible image fusion

引用

INFRARED pHYSICS & TECHNOLOGY 2025年 147卷

作者： Xia, Menghan Lin, Cheng Xu, Biyun Li, Qian Fang, Hao Huang, Zhenghua Wuhan Inst Technol Hubei Key Lab Opt Informat & Pattern Recognit Wuhan 430205 Peoples R China Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Peoples R China Wuhan Donghu Univ Sch Elect Informat Engn Wuhan 430212 Peoples R China

It is important to simultaneously preserve detail and semantic information in both infrared and visible (especially low-light) images for the pursuit of high-quality fusion maps. Unfortunately, the existing fusion methods fails to balance them, resulting in the fusion results are over-smoothed, low-contrast, and sensitive to application scenarios. To address these problems, this paper develops a detail-semantic-aware network low-light infared and visible image fusion, termed as DSAFusion. Our DSAFusion mainly includes the following key parts: Firstly, a dual-branch encoder is employed to extract the detail and semantic features in infrared and visible images. Then, the features from the two typical modes are respectively concatenated and fused detail and semantic information fusion networks (respectively named as DFNet and SFNet). Finally, the fused features contribute to reconstruct the final fusion map by a decoder to decode them. Experimental results both quantitation and qualification show that our DSAFusion is effective and performs better than the existing SOTA fusion methods on the preservation of textures and semantic information.

关键词： Infrared and low-light visible images Image fusion Detail-semantic-aware network Auto-encoder Decoder

来源：评论

学校读者我要写书评

暂无评论

Long-term and short-term memory networks based on forgetting memristors

引用

SOFT COMpUTING 2023年第23期27卷 18403-18418页

作者： Liu, Yi Chen, Ling Li, Chuandong Liu, Xin Zhou, Wenhao Li, Ke Southwest Univ Chongqing Key Lab Nonlinear Circuits & Intelligent Elect Informat & Engn Chongqing 400715 Peoples R China Lappeenranta Lahti Univ Technol LUT Sch Engn Sci Comp Vis & Pattern Recognit Lab Lappeenranta Finland

The hardware circuit of neural network based on forgetting memristors not only has the characteristics of high computational efficiency and low power consumption, but also has the advantage that a memristor can store the weight of long-term memory and short-term memory. Neural networks based on forgetting memristors can process two different data sets;however, the number of data sets processed is determined by the conversion rate of short-term memory to long-term memory neural network. In this paper, a forgetting memristor model with controllable decay rate is proposed, the short-term memory and long-term memory of the long-term and short-term memory (LSTM) network based on forgetting memristor is proposed, and the conversion speed from short-term memory network to long-term memory network is controllable. In the process of transformation from short-term memory to long-term memory of LSTM network based on forgetting memristor, the decay rate of forgetting memristor can be controlled, and the duration of short-term memory of LSTM network can be set. A reset signal mechanism is proposed so that the state of short-term memory of LSTM network with high recognition rate can be controlled. Based on the proposed controllable decay rate and reset signal, the state of the short-term memory network with high recognition rate can be set, so the LSTM network with two states can realize the recognition of different number of images under different data sets. Finally, two kinds of data sets are tested on the LSTM network based on the forgetting memristor, and the recognition rate is good, which shows the effectiveness of the proposed algorithm.

关键词： Image classification Forgetting memristor Long- and short-term memory network Fixed decay Synchronous decay

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：