检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Zhaoyu Shan, Zhengyang Chang, Jingwen Jiang, Kaixun Yang, Dingkang Cheng, Yiting Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China

Semantic segmentation is a fundamental visual task that finds extensive deployment in applications with security-sensitive considerations. Nonetheless, recent work illustrates the adversarial vulnerability of semantic segmentation models to white-box attacks. However, its adversarial robustness against black-box attacks has not been fully explored. In this paper, we present the first exploration of black-box decision-based attacks on semantic segmentation. First, we analyze the challenges that semantic segmentation brings to decision-based attacks through the case study. Then, to address these challenges, we first propose a decision-based attack on semantic segmentation, called Discrete Linear Attack (DLA). Based on random search and proxy index, we utilize the discrete linear noises for perturbation exploration and calibration to achieve efficient attack efficiency. We conduct adversarial robustness evaluation on 5 models from Cityscapes and ADE20K under 8 attacks. DLA shows its formidable power on Cityscapes by dramatically reducing PSPNet’s mIoU from an impressive 77.83% to a mere 2.14% with just 50 queries. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Character-Level Street View Text Spotting Based on Deep Multisegmentation Network for Smarter Autonomous Driving

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 297-308页

作者： Zhang, Chongsheng Tao, Yuefeng Du, Kai Ding, Weiping Wang, Bin Liu, Ji Wang, Wei Henan Provincial Key Laboratory of Big Data Analysis and Processing Laboratory of the Yellow River Cultural Heritage Henan University Kaifeng475001 China School of Information Science and Technology Nantong University Nantong226019 China School of Electrical Engineering Zhejiang University Hangzhou310058 China Big Data Lab Baidu Inc. Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

Urban scenes are full of street entities with sign boards. Therefore, in autonomous driving, street view text spotting techniques will play a significant role in the precise understanding of surrounding scenes during driving, because texts contained in the images usually provide important clues for accurate image understanding, while it is often ambiguous for existing computer vision algorithms to understand scene images without texts. In this work, we propose a Multi-Segmentation network for character-level scene Text Detection (MSTD). The MSTD introduces a densely connected atrous spatial pyramid pooling module to enlarge the receptive field of the feature extraction layer, so as to localize long as well as large-sized text instances. Moreover, it devises a double segmentation subnetwork to utilize two independent but inherently complementary losses to co-optimize the network and increase the reliability of the confidence scores in predicting the text/nontext areas. With the character instances detected by the MSTD, one can easily perform scene text spotting with classic object recognition networks such as ResNet and DenseNet. We carried out extensive experiments on nine scene text datasets to demonstrate the outstanding performance of the MSTD on character-level and line-level text instance localization and scene text recognition, where the MSTD significantly outperforms the state-of-the-art scene text detection methods and the sequence-to-sequence-learning-based scene text recognizers. © 2020 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Lei Zhan, Yibing Ma, Leilei Tao, Dapeng Ding, Liang Gong, Chen Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Jiangsu Nanjing210094 China JD Explore Academy Beijing100000 China Anhui University School of Computer Science and Technology Anhui Heifei230601 China Yunnan University FIST LAB School of Information Science and Engineering Yunnan Kunming650091 China

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this article, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice"in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias;2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also provide a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the potential of extending our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://***/zuiran/SpliceMix. © 1999-2012 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

DeTrack: In-model Latent Denoising Learning for Visual Object Tracking

arXiv

引用

arXiv 2025年

作者： Zhou, Xinyu Li, Jinglun Hong, Lingyi Jiang, Kaixun Guo, Pinxue Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Anisotropic electrical properties of aligned PtSe_(2) nanoribbon arrays grown by a pre-patterned selective selenization process

引用

Nano Research 2022年第5期15卷 4668-4676页

作者： Huaipeng Wang Zhifang Liu Yilin Sun Xiaofan Ping Jianlong Xu Yingtao Ding Haowen Hu Dan Xie Tianling Ren School of Integrated Circuits Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijing 100084China Department of Chemistry Tsinghua UniversityBeijing 100084China School of Integrated Circuits and Electronics Beijing Institute of TechnologyBeijing 100081China Institute of Functional Nano&Soft Materials(FUNSOM) Jiangsu Key Laboratory for Carbon-Based Functional Materials&DevicesSoochow UniversitySuzhou 215123China State Key Lab of New Ceramics and Fine Processing School of Materials Science and EngineeringTsinghua UniversityBeijing 100084China

This study proposes a feasible and scalable production strategy to naturally obtain aligned platinum diselenide(PtSe_(2))nanoribbon arrays with anisotropic *** anisotropic properties of two-dimensional(2D)materials,especially transition-metal dichalcogenides(TMDs),have attracted great interest in *** dependence of physical properties on their lattice orientations is of particular interest because of its potential in diverse applications,such as nanoelectronics and ***-dimensional(1D)nanostructures facilitate many feasible production strategies for shaping 2D materials into unidirectional 1D nanostructures,providing methods to investigate the anisotropic properties of 2D materials based on their lattice orientations and *** natural alignment of zigzag(ZZ)PtSe_(2) nanoribbons is experimentally demonstrated using angle-resolved polarized Raman spectroscopy(ARPRS),and the selective growth mechanism is further theoretically revealed by comparing edges and edge energies of different orientations using the density functional theory(DFT).Back-gate field-effect transistors(FETs)are also constructed of unidirectional PtSe_(2) nanoribbons to investigate their anisotropic electrical properties,which align with the results of the projected density of states(DOS)*** work provides new insight into the anisotropic properties of 2D materials and a feasible investigation strategy from experimental and theoretical perspectives.

关键词： PtSe_(2) scalable production anisotropic properties nanoribbons density functional theory

来源：评论

学校读者我要写书评

暂无评论

HiDiff: Hybrid Diffusion Framework for Medical Image Segmentation

arXiv

引用

arXiv 2024年

作者： Chen, Tao Wang, Chenhui Chen, Zhihao Lei, Yiming Shan, Hongming Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China

Medical image segmentation has been significantly advanced with the rapid development of deep learning (DL) techniques. Existing DL-based segmentation models are typically discriminative;i.e., they aim to learn a mapping from the input image to segmentation masks. However, these discriminative methods neglect the underlying data distribution and intrinsic class characteristics, suffering from unstable feature space. In this work, we propose to complement discriminative segmentation methods with the knowledge of underlying data distribution from generative models. To that end, we propose a novel hybrid diffusion framework for medical image segmentation, termed HiDiff, which can synergize the strengths of existing discriminative segmentation models and new generative diffusion models. HiDiff comprises two key components: discriminative segmentor and diffusion refiner. First, we utilize any conventional trained segmentation models as discriminative segmentor, which can provide a segmentation mask prior for diffusion refiner. Second, we propose a novel binary Bernoulli diffusion model (BBDM) as the diffusion refiner, which can effectively, efficiently, and interactively refine the segmentation mask by modeling the underlying data distribution. Third, we train the segmentor and BBDM in an alternate-collaborative manner to mutually boost each other. Extensive experimental results on abdomen organ, brain tumor, polyps, and retinal vessels segmentation datasets, covering four widely-used modalities, demonstrate the superior performance of HiDiff over existing medical segmentation algorithms, including the state-of-the-art transformer- and diffusion-based ones. In addition, HiDiff excels at segmenting small objects and generalizing to new datasets. Source codes are made available at https://***/takimailto/HiDiff. Copyright © 2024, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Neural Underwater Scene Representation

Neural Underwater Scene Representation

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yunkai Tang Chengxuan Zhu Renjie Wan Chao Xu Boxin Shi National Engineering Research Center of Visual Technology School of Computer Science Peking University National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Key Lab of General AI School of Intelligence Science and Technology Peking University Department of Computer Science Hong Kong Baptist University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Among the numerous efforts towards digitally recovering the physical world, Neural Radiance Fields (NeRFs) have proved effective in most cases. However, underwater scene introduces unique challenges due to the absorbing water medium, the local change in lighting and the dynamic contents in the scene. We aim at developing a neural under-water scene representation for these challenges, modeling the complex process of attenuation, unstable in-scattering and moving objects during light transport. The proposed method can reconstruct the scenes from both established datasets and in-the-wild videos with outstanding fidelity.

关键词： Solid modeling Visualization Computational modeling Urban areas Lighting Virtual reality Neural radiance field

来源：评论

学校读者我要写书评

暂无评论

EC-SLAM: Effectively Constrained Neural RGB-D SLAM with Sparse TSDF Encoding and Global Bundle Adjustment

arXiv

引用

arXiv 2024年

作者： Li, Guanghao Chen, Qi Yan, Yuxiang Pu, Jian Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China

We introduce EC-SLAM, a real-time dense RGB-D simultaneous localization and mapping (SLAM) system leveraging Neural Radiance Fields (NeRF). While recent NeRF-based SLAM systems have shown promising results, they have yet to fully exploit NeRF’s potential to constrain pose optimization. EC-SLAM addresses this by using sparse parametric encodings and Truncated Signed Distance Fields (TSDF) to represent the map, enabling efficient fusion, reducing model parameters, and accelerating convergence. Our system also employs a globally constrained Bundle Adjustment (BA) strategy that capitalizes on NeRF’s implicit loop closure correction capability, improving tracking accuracy by reinforcing constraints on keyframes most relevant to the current optimized frame. Furthermore, by integrating a feature-based and uniform sampling strategy that minimizes ineffective constraint points for pose optimization, we reduce the impact of random sampling in NeRF. Extensive evaluations on the Replica, ScanNet, and TUM datasets demonstrate state-of-the-art performance, with precise tracking and reconstruction accuracy achieved alongside real-time operation at up to 21 Hz. The source code is available at https://***/Lightingooo/EC-SLAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Prototype-based classifier learning for long-tailed visual recognition

引用

Science China(information Sciences) 2022年第6期65卷 62-76页

作者： Xiu-Shen WEI Shu-Lin XU Hao CHEN Liang XIAO Yuxin PENG School of Computer Science and Engineering Nanjing University of Science and Technology State Key Laboratory of Integrated Services Networks Xidian University Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security Wangxuan Institute of Computer Technology Peking University

In this paper, we tackle the long-tailed visual recognition problem from the categorical prototype perspective by proposing a prototype-based classifier learning(PCL) method. Specifically, thanks to the generalization ability and robustness, categorical prototypes reveal their advantages of representing the category semantics. Coupled with their class-balance characteristic, categorical prototypes also show potential for handling data imbalance. In our PCL, we propose to generate the categorical classifiers based on the prototypes by performing a learnable mapping function. To further alleviate the impact of imbalance on classifier generation, two kinds of classifier calibration approaches are designed from both prototype-level and example-level aspects. Extensive experiments on five benchmark datasets, including the large-scale iNaturalist, Places-LT,and ImageNet-LT, justify that the proposed PCL can outperform state-of-the-arts. Furthermore, validation experiments can demonstrate the effectiveness of tailored designs in PCL for long-tailed problems.

关键词： long-tailed distribution categorical prototype classifier generation classifier calibration class imbalance

来源：评论

学校读者我要写书评

暂无评论

Video Captioning via Relation-Aware Graph Learning

Video Captioning via Relation-Aware Graph Learning

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yi Zheng Heming Jing Qiujie Xie Yuejie Zhang Rui Feng Tao Zhang Shang Gao School of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University China School of Information Management and Engineering Shanghai University of Finance and Economics China School of Information Technology Deakin University Australia

Recent neural models for video captioning usually employed an encoder-decoder framework. However, most approaches either neglected the spatial and temporal interactions between objects in a video or implicitly modelled the interactions, resulting in less desired performance. In this paper, we propose a novel relation-aware graph learning framework. It explicitly models both spatial and temporal relations for objects. In particular, a relation-aware graph is designed to depict the spatial relations between different objects in a scene. Parallelly, a temporal graph network is designed to perform relational reasoning for the same objects in adjacent frames. Features of both types of relations are learned and fused for the follow-up language decoder. Experiments on two bench-mark datasets show the effectiveness of our framework. It achieves state-of-the-art performance with CIDEr scores on MSVD and MSR-VTT.

关键词： Visualization Signal processing Cognition Acoustics Decoding Speech processing

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：