检索结果-内蒙古大学图书馆

LGSNet: Local-Global Semantics Learning Object Detection

IEEE Transactions on Multimedia 2025年 27卷 2281-2292页

作者： Li, Yang Jiao, Licheng Liu, Xu Liu, Fang Li, Lingling Chen, Puhua Xidian University Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China International Research Center of Intelligent Perception and Computation School of Artificial Intelligence Xi'an710126 China

Self-attention learns capturing the long-range dependencies between embeddings (e.g., image pixels). However, the memory overhead and computation cost are prohibitive due to being quadratic in term of the spatial resolution. The structure analysis reveals two crucial roles in the attention: the correlation-based dependency structure and feature normalization. In this work, an efficacious Local-Global Semantics (LGS) module is proposed to alleviate the above issues by modeling the local semantic aggregation and global semantic interaction. Our LGS module contains a group convolution and an Efficient Global Semantic Attention (EGSA). Firstly, the group convolution aggregates local semantics. Secondly, considering a feature map as a sequence of 2-D channel representations, EGSA formulates a general model for the global semantic interaction. The linear correlation is computed between global semantics. LGS has the linear memory overhead and computation cost in term of the spatial resolution. The LGS module can be smoothly incorporated into object detection frameworks. The experiment results verify its effectiveness on two popular detection datasets: the MS COCO and PASCAL VOC. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Joint Style and Layout Synthesizing: Toward Generalizable Remote Sensing Semantic Segmentation

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第5期35卷 4055-4071页

作者： Zang, Qi Wang, Shuang Zhao, Dong Zhong, Zhun Hou, Biao Jiao, Licheng Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Shaanxi Xi’an710071 China Hefei University of Technology School of Computer Science and Information Engineering Anhui Hefei230601 China

This paper studies the domain generalized remote sensing semantic segmentation (RSSS), aiming to generalize a model trained only on the source domain to unseen domains. Existing methods in computer vision treat style information as domain characteristics to achieve domain-agnostic learning. Nevertheless, their generalizability to RSSS remains constrained, due to the incomplete consideration of domain characteristics. We argue that remote sensing scenes have layout differences beyond just style. Considering this, we devise a joint style and layout synthesizing framework, enabling the model to jointly learn out-of-domain samples synthesized from these two perspectives. For style, we estimate the variant intensities of per-class representations affected by domain shift and randomly sample within this modeled scope to reasonably expand the boundaries of style-carrying feature statistics. For layout, we explore potential scenes with diverse layouts in the source domain and propose granularity-fixed and granularity-learnable masks to perturb layouts, forcing the model to learn characteristics of objects rather than variable positions. The mask is designed to learn more context-robust representations by discovering difficult-to-recognize perturbation directions. Subsequently, we impose gradient angle constraints between the samples synthesized using the two ways to correct conflicting optimization directions. Extensive experiments demonstrate the superior generalization ability of our method over existing methods. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Contour Knowledge-Aware perception Learning for Semantic Segmentation

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第5期35卷 4560-4575页

作者： You, Chao Jiao, Licheng Li, Lingling Liu, Xu Liu, Fang Ma, Wenping Yang, Shuyuan Xidian University Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education of China International Research Center of Intelligent Perception and Computation School of Artificial Intelligence Xi’an710071 China Xi’an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an710049 China

The diversity of contextual information is of great importance for accurate semantic segmentation. However, most methods focus on single spatial contextual information, which results in an overlap of the semantic content of categories and a loss of contour information of objects. In this article, we propose a novel contour knowledge-aware perception learning network (CKPL-Net) to capture diverse contextual information by space-category aggregation module (SCAM) and contour-aware calibration module (CACM). First, SCAM is introduced to enhance intraclass consistency and interclass differentiation of features. By integrating space-aware and category-aware attention, SCAM reduces the redundancy of features from a categorical perspective while maintaining spatial correlation of pixels, substantially avoiding the overlap of the semantic content in categories. Second, CACM is designed to maintain the integrity of objects by perceiving contour contextual information. It develops a novel contour-aware knowledge and adaptively transforms the grid structure of convolutions for boundary pixels, which effectively calibrates the representation of features near boundaries. Finally, the quantitative and qualitative analyses on the three public datasets: ISPRS Potsdam dataset, ISPRS Vaihingen dataset, and WHDLD dataset, demonstrate that the proposed CKPL-Net achieves superior performance compared with prevalent methods, which indicates diverse contextual information is beneficial for accurate segmentation. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

MLMamba: A Mamba-based Efficient Network for Multi-label Remote Sensing Scene Classification

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Du, Ruiqi Tang, Xu Ma, Jingjing Zhang, Xiangrong Jiao, Licheng Xidian University School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education China

As a useful remote sensing (RS) scene interpretation technique, multi-label RS scene classification (RSSC) always attracts researchers' attention and plays an important role in the RS community. To assign multiple semantic labels to a single RS image according to its complex contents, the existing methods focus on learning the valuable visual features and mining the latent semantic relationships from the RS images. This is a feasible and helpful solution. However, they are often associated with high computational costs due to the widespread use of Transformers. To alleviate this problem, we propose a Mamba-based efficient network based on the newly emerged state space model called MLMamba. In addition to the basic feature extractor (convolutional neural network and language model) and classifier (multiple perceptrons), MLMamba consists of two key components: a pyramid Mamba and a feature-guided semantic modeling (FGSM) Mamba. Pyramid Mamba uses multi-scale scanning to establish global relationships within and across different scales, improving MLMamba's ability to explore RS images. Under the guidance of the obtained visual features, FGSM Mamba establishes associations between different land covers. Combining these two components can deeply mine local features, multi-scale information, and long-range dependencies from RS images and build semantic relationships between different surface covers. These superiorities guarantee that MLMamba can fully understand the complex contents within RS images and accurately determine which categories exist. Furthermore, the simple and effective structure and linear computational complexity of the state space model ensure that pyramid Mamba and FGSM Mamba will not impose too much computational burden on MLMamba. Extensive experiments counted on three benchmark multi-label RSSC data sets validate the effectiveness of MLMamba. The positive results demonstrate that MLMamba achieves state-of-the-art performance, surpassing existing meth

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SAR target recognition network based on frequency domain covariance matrix and Riemannian manifold

引用

Geomatica 2025年第1期77卷

作者： Guo, Zhengxi Hou, Biao Yang, Chen Guo, Xianpeng Wu, Zitong Ren, Bo Jiao, Licheng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Shaanxi Province Xi'an710071 China

Synthetic Aperture Radar (SAR) image target recognition is a critical problem in remote sensing. Traditional deep learning-based methods often overlook the rich information in the frequency domain of SAR images. Existing frequency domain based approaches typically rely on prior knowledge to select different frequency components or guide network learning, failing to fully exploit the information contained in the frequency domain. We believe that knowledge from the macroscopic high-dimensional space needs to be harnessed to learn about the frequency domain. Therefore, in this paper, we propose an innovative SAR target recognition framework known as FDCM-Net (Frequency Domain Covariance Matrix and Riemannian Manifold Network). Our method integrates the frequency domain information of SAR images with the covariance matrix, revealing the complex relationships between different frequency components and delving into the latent features within the frequency domain. Additionally, we explore the geometric properties of the covariance matrix and design an innovative network architecture based on Riemannian manifold theory. This network effectively captures important information from the frequency domain of SAR images in high-dimensional space while preserving the geometric characteristics of the original data and performing classification. We conducted comprehensive evaluations of FDCM-Net using the MSTAR, OpenSARShip 2.0 and FUSAR-Ship 1.0 datasets. Our results demonstrate that FDCM-Net outperforms previous methods based on spatial and frequency domain baselines in terms of classification performance. © 2025 key laboratory of intelligent perception and image understanding of Ministry of education, Xidian University

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A 3D Self-Awareness Diffusion Network for Multimodal Classification

引用

IEEE Transactions on Multimedia 2025年

作者： Ma, Mengru Ma, Wenping Jiao, Licheng Li, Lingling Liu, Xu Liu, Fang Yang, Shuyuan Guo, Yuwei Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation School of Artificial Intelligence Xi'an710071 China

As imaging sensor technology in remote sensing has advanced quickly, multimodal fusion classification has become an important research direction in land cover and urban planning classification tasks. While generative models and image classification have greatly benefited from diffusion models, the present ones primarily concentrate on single-modality-driven diffusion processes. Therefore, this paper presents a 3D self-awareness diffusion network (3DSA-DiffNet) for multispectral (MS) and panchromatic (PAN) image fusion classification, which would make it easier to classify heterogeneous data from various sensors. First, in order to model the relationship between multi-channel spectra and multi-pixel spatial distributions as well as samples, respectively, a spatial-spectral joint denoising network (S2 JD-Net) is proposed. It can incorporate the diffusion process into the neural network to enhance the quality of diffusion features. Secondly, to imitate the brain's spatial-spectral coexistence learning mechanism, this work offers a 3D self-awareness module (3DSA-Module) that can learn the weight of each pixel in 3D space, resulting in extraordinarily high feature representation capabilities. Finally, experimental verification demonstrates that the 3D self-awareness diffusion fusion network driven by brain inspiration outperforms more sophisticated approaches on the Xi'an, Huhhot, and Muufl datasets. © 1999-2012 IEEE.

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Complex Wavelet Informed Transformer Operator

引用

IEEE Transactions on Multimedia 2025年

作者： Li, Xiaotong Jiao, Licheng Liu, Fang Yang, Shuyuan Zhu, Hao Liu, Xu Li, Lingling Ma, Wenping Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Joint International Research Laboratory of Intelligent Perception and Computation School of Artificial Intelligence Shaanxi Xi'an710071 China

Visual transformers have achieved great success in representation learning. This is mainly due to efficient token dependency modeling via self-attention. However, the computational burden increases sharply as the input pixels increase. Although recent Fourier-based global frequency-domain mixing methods attempt to improve the efficiency of transformers for high-resolution image inputs, the Fourier operator has limited ability to capture the local geometric structure. Complex wavelets can perform local attention in both the spatial domain and the frequency domain. Therefore, we propose the complex wavelet informed transformer operator that uses the real and imaginary wavelets of the dual-tree complex wavelet transform to simulate the interaction in the attention kernel. In order to further reduce the computational burden of operators, we introduce an adaptive local block shared attention mechanism in the channel domain for our wavelet informed operators. Further, we construct the deep multi-head operator network consisting of a hybrid stack of complex wavelet informed transformer operators and self-attention layers. This enables the Transformer to more sparsely capture multi-scale and multi-directional structured features in the process of learning dependencies. Extensive experimental results show that our adaptive complex wavelet informed transformer operator under the Transformer architecture achieves highly competitive accuracy performance on multiple image classification benchmark datasets. And the proposed operators can be flexibly and effectively migrated to vision tasks in dynamic video scenarios. Codes are available at https://***/Dawn5786/ACWI-Former. © 1999-2012 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Change Knowledge-Guided Vision-Language Remote Sensing Change Detection

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Wang, Jiahao Liu, Fang Jiao, Licheng Wang, Hao Li, Shuo Li, Lingling Chen, Puhua Liu, Xu Ma, Wenping Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Joint International Research Laboratory of Intelligent Perception and Computation School of Artificial Intelligence Shaanxi Xi’an710071 China

Remote sensing image change detection plays a critical role in applications like video surveillance and geographic information systems. However, existing binary and semantic change detection methods often rely solely on visual information, neglecting language information, which limits interpretability and the ability to provide specific change details. This work proposes the Change Knowledge-Guided Vision-Language Remote Sensing Change Detection (CKCD) method to address these limitations. By introducing change knowledge as language information, CKCD enhances semantic understanding and change detail representation. A Cross-Modal Affinity (CMA) module is designed to effectively fuse visual and textual features, improving information complementarity and fusion coherence. CKCD further enhances data utilization efficiency by merging change area detection and change category information into a single output through endto- end learning. This design reduces redundant data representations and simplifies the detection process, leading to a more compact and efficient use of the input data without requiring additional branches or multiple output heads. Experimental results demonstrate consistent performance improvements over traditional methods across multiple change detection datasets. © 1980-2012 IEEE.

关键词： change category information Change Detection Change Knowledge visual and textual modalities

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Semi-supervised Learning Segmentation for Remote Sensing images

引用

IEEE Transactions on Multimedia 2025年

作者： Lu, Xiaoqiang Li, Lingling Jiao, Licheng Liu, Xu Liu, Fang Ma, Wenping Yang, Shuyuan Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation School of Artificial Intelligence Shaanxi Province Xi'an710071 China

Deep learning based remote sensing (RS) image segmentation significantly impacts several real application scenarios. Behind its success, massive labeled data plays an important role. However, annotating high-resolution RS images requires time-consuming and relevant expertise efforts. To address it, many works dive into semi-supervised learning which utilizes raw information embedded in unlabeled data to improve the segmentation model. Nevertheless, previous studies ignore the integrity and effectiveness of the potential context information hidden in RS data. In this work, we propose an uncertainty-aware masked consistency learning (U-MCL) framework that contains an uncertainty-aware masked denoising (U-MD) module and an uncertainty-aware masked image consistency (U-MIC) module. U-MCL initially generates a patch-wise uncertainty map for each unlabeled image during each training iteration, which is then used to derive an adaptive mask ratio for pseudo-label denoising in U-MD. Simultaneously, the uncertainty map is adopted to model a masked unlabeled image for reasoning unseen areas in U-MIC. Consequently, U-MCL is capable of enhancing model performance by engaging in accurate and stable consistency learning while preserving the integrity of the context and employing the context to infer the predictions of the masked regions safely. Extensive experiments on six RS datasets, i.e., ISPRS Vaihingen, FloodNet, MiniFrance, LoveDA, MER, and MSL, demonstrate the superiority of our U-MCL over recent most advanced methods, achieving new state-of-the-art performance under all benchmarks. Code will be available at https://***/xiaoqiang-lu/U-MCL. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Aware Evolutionary Transformer

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Zhang, Ruohan Li, Lingling Jiao, Licheng Liu, Fang Liu, Xu Yang, Shuyuan Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Shaanxi Province Xi'an710071 China

With the Transformer architecture achieving impressive results in the vision domain. It has become a current popular research to explore more potentials of Transformer mixed architectures and explore more suitable mixed combinations. In this paper, Transformer classification network is designed and explored by multi-task architecture search algorithm. A new paradigm for multi-task architecture is designed by combining convolution and Transformer. The designed search architecture can combine the respective advantages of convolution and Transformer and can obtain better performance. At the same time, corresponding knowledge-aware multi-task genetic operators are designed to generate offspring individuals. Inter-task and inter-experience knowledge-aware is utilised to facilitate evolutionary convergence. During the search process, the reference evaluation method is utilised to reduce the redundant computation and time during the search process. In the experimental section, the search results are compared with state-of-the-art architectures and search algorithms. The experimental results confirm the effectiveness and high generalisation of the searched architectures. The ablation experimental part proves the effectiveness of the proposed architectural paradigm, genetic operators and reference evaluation. © 2025 IEEE.

关键词： Convolution

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：