检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liu, Chenguang Feng, Yongchao Zhang, Yanan Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Hangzhou Innovation Institute Beihang University Hangzhou310051 China

In recent years, there has been significant advancement in object detection. However, applying off-the-shelf detectors to a new domain leads to significant performance drop, caused by the domain gap. These detectors exhibit higher-variance class-conditional distributions in the target domain than that in the source domain, along with mean shift. To address this problem, we propose the Prototype Augmented Compact Features (PACF) framework to regularize the distribution of intra-class features. Specifically, we provide an in-depth theoretical analysis on the lower bound of the target features-related likelihood and derive the prototype cross entropy loss to further calibrate the distribution of target RoI features. Furthermore, a mutual regularization strategy is designed to enable the linear and prototype-based classifiers to learn from each other, promoting feature compactness while enhancing discriminability. Thanks to this PACF framework, we have obtained a more compact cross-domain feature space, within which the variance of the target features’ class-conditional distributions has significantly decreased, and the class-mean shift between the two domains has also been further reduced. The results on different adaptation settings are state-of-the-art, which demonstrate the board applicability and effectiveness of the proposed approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Depth-continuous Scene Representation with Displacement Field for Robust Light Field Depth Estimation

引用

IEEE Transactions on Multimedia 2025年

作者： Chen, Rongshan Sheng, Hao Yang, Da Cong, Ruixuan Cui, Zhenglong Wang, Sizhe Wang, Tun Zhao, Mingyuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing International Innovation Institute 166 Shuanghongqiao Street Pingyao Town Yuhang District Hangzhou31 1115 China Macao Polytechnic University Faculty of Applied Sciences Macao999078 China

The light field (LF) captures both the spatial and angular information of scenes, enabling accurate depth estimation. However, previous deep learning methods typically model surface depth only while ignoring the continuous nature of depth in 3D scenes. In this paper, we use the displacement field (DF) to describe this continuous property, and propose a novel depth-continuous scene representation for robust LF depth estimation. Experiments demonstrate that our representation enables the network to generate highly detailed depth maps with fewer parameters and faster speeds. Specifically, inspired by the signed distance field in 3D object descriptions, we aim to exploit the intrinsic depth-continuous property of 3D scenes via DF and define a novel depth-continuous scene representation. Then, we introduce a simple, yet general, learning framework for depth-continuous scene embedding, and the proposed network, DepthDF, achieves state-of-the-art performance on both synthetic and real-world LF datasets, ranking 1st on the HCI 4D light field benchmark. Furthermore, previous LF depth estimation methods can also be seamlessly integrated into this framework. Finally, we extend this framework beyond LF depth estimation to various tasks, including multiview stereo depth inference, LF superresolution, and LF salient object detection. Our experiments demonstrate an improved performance when continuous scene representation is applied, suggesting that our framework can potentially provide insights for more fields. © 1999-2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Four-dimension efficient pixel-frequency transformer for light field spatial and angular super-resolution

引用

Engineering Applications of Artificial Intelligence 2025年 154卷

作者： Wang, Sizhe Sheng, Hao Cong, Ruixuan Yang, Da Chen, Rongshan Cui, Zhenglong State Key Laboratory of Electromechanical Integrated Manufacturing of High-Performance Electronic Equipments School of Mechano-Electronic Engineering Xidian University Shannxi Xi'an710071 China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Key Laboratory of Data Science and Intelligent Computing International Innovation Institute Beihang University Zhejinag Hangzhou311115 China Faculty of Applied Sciences Macao Polytechnic University 999078 China

Super-resolution plays an important role in optical engineering, which can offer high-quality image information for vision applications. The light field camera can capture the intensity and direction information of light, providing abundant scene information. However, it faces the trade-off problem of spatial and angular resolution. Benefiting from global context modeling by self-attention mechanism, transformer-based artificial intelligence methods for the light field (LF) super-resolution (SR) provide superior performance. However, in these methods, the four-dimensional (4D) LF is reshaped into a large one-dimensional (1D) sequence to be processed, which leads to a significant increase in computation and memory and raises difficulties of 4D structure reconstruction for LF spatial and angular SR. This paper presents a 4D efficient pixel-frequency transformer (4DEPFT) for spatial and angular SR, which models 4D correlation in the pixel and frequency domains based on the proposed inner-outer transformer with 4D position encoding. Specifically, two parallel branches separately handle LF images and their corresponding frequency maps in 4DEPFT. In the pixel branch, sub-patch-based inner-outer pixel transformers are proposed to extract 4D pixel features inside and outside local windows, which deal with pixels with small and large disparity shifts separately. In the frequency branch, a multi-band-based inner-outer frequency transformer is proposed to reconstruct 4D frequency features from different frequency bands. Finally, an attention-based pixel and frequency feature fusion module is presented to acquire the high-resolution LF. Experimental results on real-world and simulated public datasets indicate that 4DEPFT outperforms other methods with less computational cost and graphics processing unit (GPU) consumption. © 2025 Elsevier Ltd

关键词： Photonics

来源：评论

学校读者我要写书评

暂无评论

Online Self-distillation and Self-modeling for 3D Brain Tumor Segmentation

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Pang, Yan Li, Yunhao Huang, Teng Liang, Jiaming Wang, Zhen Dong, Changyu Kuang, Dongyang Hu, Ying Chen, Hao Lei, Tim Wang, Qiong The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China The School of Artificial Intelligence Guangzhou University China The Zhejiang Lab Hangzhou China Sun Yat-sen University China The Department of Computer Science and Engineering The Department of Chemical and Biological Engineering Hong Kong University of Science and Technology China The Department of Electrical Engineering University of Colorado Denver United States

In the specialized domain of brain tumor segmentation, supervised segmentation approaches are hindered by the limited availability of high-quality labeled data, a condition arising from data privacy concerns, significant costs, and ethical issues. In response to this challenge, this paper presents a training framework that adeptly integrates a plug-and-play component, MOD, into current supervised learning models, boosting their efficacy in scenarios with limited data. The MOD consists of an Online Tokenizer and a Dense Predictor, which employs self-distillation and self-modeling on masked patches, promoting swift convergence and efficient representation learning. During the inference phase, the plug-and-play MOD component is excluded, preserving the computational efficiency of the original model without incurring extra processing costs. We substantiated the value of our approach through experiments on leading 3D brain tumor segmentation baselines. Remarkably, models augmented with the MOD consistently showcased superior results, achieving elevated Dice coefficients and HD95 scores on two datasets: BraTS 2021 and MSD 2019 Task-01 Brain Tumor. Code: https://***/aigzhusmart/MOD © 2013 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

CR-Famba: A Frequency-Domain Assisted Mamba for Thin Cloud Removal in Optical Remote Sensing Imagery

引用

IEEE Transactions on Multimedia 2025年

作者： Liu, Jiao Pan, Bin Shi, Zhenwei Nankai University TKLNDST College of Computer Science Tianjin300350 China Nankai University School of Statistics and Data Science KLMDASR LEBPS LPMC Tianjin300071 China Beihang University Image Processing Center School of Astronautics the State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China

Optical remote sensing images are inevitably affected by cloud cover. To remove clouds from optical remote sensing images, a series of deep learning-based thin cloud removal methods have been developed. However, these methods have not explored the long-range modeling ability of state space models in optical remote sensing image thin cloud removal. In this paper, we propose a frequency-domain assisted Mamba for thin cloud removal, which is called CR-Famba. In CR-Famba, to better extract global and local features of images, we design a frequency-domain assisted state space layer (FDA-SSL). The FDA-SSL consists of two core components: residual state space block (RSSB) and frequency domain detail enhancement block (FDDEB). The RSSB utilizes the visual state space module (VSSM) to extract long-range dependencies of images from a spatial perspective while adding convolutional layers to overcome local pixel forgetting. Due to the rich detailed information of remote sensing images, we present FDDEB equipped with discrete wavelet transform (DWT) to supplement the extracted local information from the frequency domain perspective. We conduct experiments on different types of cloud-containing datasets, and the results show that our method can recover images with clearer texture details compared to other methods. https://***/Lab-PANbin/ © 2025 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model

arXiv

引用

arXiv 2025年

作者： Liu, Chenyang Chen, keyan Zhao, Rui Zou, Zhengxia Shi, Zhenwei The Department of Aerospace Intelligent Science and Technology School of Astronautics The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies Ministry of Education China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Shen Yuan Honors College of Beihang University Beijing100191 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Recently, generative foundation models have significantly advanced large-scale text-driven natural image generation and have become a prominent research trend across various vertical domains. However, in the remote sensing field, there is still a lack of research on large-scale text-to-image (text2image) generation technology. Existing remote sensing image-text datasets are small in scale and confined to specific geographic areas and scene types. Besides, existing text2image methods have struggled to achieve global-scale, multi-resolution controllable, and unbounded image generation. To address these challenges, this paper presents two key contributions: the Git-10M dataset and the Text2Earth foundation model. Git-10M is a global-scale image-text dataset comprising 10.5 million image-text pairs, 5 times larger than the previous largest one. The dataset contains essential resolution information and covers a wide range of geographic scenes and contains essential geospatial metadata, significantly surpassing existing datasets in both size and diversity. Building on Git-10M, we propose Text2Earth, a 1.3 billion parameter generative foundation model based on the diffusion framework to model global-scale remote sensing scenes. Text2Earth integrates a resolution guidance mechanism, enabling users to specify image resolutions. A dynamic condition adaptation strategy is proposed for training and inference to improve image generation quality. Text2Earth not only excels in zero-shot text2image generation but also demonstrates robust generalization and flexibility across multiple tasks, including unbounded scene construction, image editing, and cross-modal image generation. This robust capability surpasses previous models restricted to the basic fixed size and limited scene types. On the previous text2image benchmark dataset, Text2Earth outperfoms previous models with a significant improvement of +26.23 FID and +20.95% Zero-shot Cls-OA metric. Our project page is https://chen-y

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Structural properties and generative model of non-giant connected components in social networks

引用

Science China Earth Sciences 2016年第12期59卷 229-234页

作者： Jianwei NIU Lei WANG State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University

Most previous studies have mainly focused on the analyses of one entire network(graph) or the giant connected components of networks. In this paper, we investigate the disconnected components(non-giant connected component) of some real social networks, and report some interesting discoveries about structural properties of disconnected components. We study three diverse, real networks and compute the significance profile of each component. We discover some similarities in the local structure between the giant connected component and disconnected components in diverse social networks. Then we discuss how to detect network attacks based on the local structure properties of networks. Furthermore, we propose an empirical generative model called i Friends to generate networks that follow our observed patterns.

关键词： disconnected components giant connected component structural properties significance profile generative model

来源：评论

学校读者我要写书评

暂无评论

Semantic part segmentation of single-view point cloud

引用

Science China(Information Sciences) 2020年第12期63卷 251-253页

作者： Haotian PENG Bin ZHOU Liyuan YIN Kan GUO Qinping ZHAO State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University

As a classic topic in computer graphics, the semantic part segmentation of 3D data is helpful for3D part-level editing and modeling. Single-views point cloud is the raw format of 3D data. Giving each point a semantic annotation in single-view point cloud, i.e., single-view point cloud semantic part segmentation, is meaningful and challenging.

关键词： computers and graphics single-view point cloud annotation transfer semantic part segmentation category independent matching point clouds registration

来源：评论

学校读者我要写书评

暂无评论

Localizing object parts in 3D from a single image

引用

Science China(Information Sciences) 2019年第7期62卷 217-219页

作者： Shen YIN Bin ZHOU Mingjia YANG Yu ZHANG State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University

Object localization in 3D from 2D images is an important computer vision problem that enables modern robotic vision systems to interact properly with the objects present in the real world. Owing to its significance, techniques for recovering the 6-DOF pose and dimensions of objects from images has received increasing attention in recent years [1–3]. However, to the best of our knowledge,the existing approaches all focus on object-level inference instead of analyzing object parts. Most of

关键词： pro Localizing object parts in 3D from a single image

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：