检索结果-内蒙古大学图书馆

Interactive Multi-dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration 1

学校读者我要写书评

暂无评论

16th European Conference on Computer Vision, ECCV 2020

作者： He, Jingwen Dong, Chao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (数字)9783030585655

ISBN: (纸本)9783030585648

Interactive image restoration aims to generate restored images by adjusting a controlling coefficient which determines the restoration level. Previous works are restricted in modulating image with a single coefficient. However, real images always contain multiple types of degradation, which cannot be well determined by one coefficient. To make a step forward, this paper presents a new problem setup, called multi-dimension (MD) modulation, which aims at modulating output effects across multiple degradation types and levels. Compared with the previous single-dimension (SD) modulation, the MD is setup to handle multiple degradations adaptively and relief unbalanced learning problem in different degradations. We also propose a deep architecture - CResMD with newly introduced controllable residual connections for multi-dimension modulation. Specifically, we add a controlling variable on the conventional residual connection to allow a weighted summation of input and residual. The values of these weights are generated by another condition network. We further propose a new data sampling strategy based on beta distribution to balance different degradation types and levels. With corrupted image and degradation information as inputs, the network can output the corresponding restored image. By tweaking the condition vector, users can control the output effects in MD space at test time. Extensive experiments demonstrate that the proposed CResMD achieve excellent performance on both SD and MD modulation tasks. Code is available at https://***/hejingwenhejingwen/CResMD. © 2020, Springer Nature Switzerland AG.

关键词： Modulation

Convolutional Neural Network Based Intelligent Handwritten Document recognition

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第3期70卷 4563-4581页

作者： Sagheer Abbas Yousef Alhwaiti Areej Fatima Muhammad A.Khan Muhammad Adnan Khan Taher M.Ghazal Asma Kanwal Munir Ahmad Nouh Sabri Elmitwally School of Computer Science National College of Business administration and EconomicsLahore54000Pakistan College of Computer and Information Sciences Jouf UniversitySakaka72341Saudi Arabia Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Pattern Recognition and Machine Learning Lab Department of SoftwareGachon UniversitySeongnam13557Korea Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan Malaysia(UKM)Bangi 43600SelangorMalaysia School of Information Technology Skyline University CollegeUniversity City Sharjah1797SharjahUAE Department of Computer Science GC UniversityLahorePakistan Department of Computer Science Faculty of Computers and Artificial IntelligenceCairo University12613Egypt

This paper presents a handwritten document recognition system based on the convolutional neural network *** today’s world,handwritten document recognition is rapidly attaining the attention of researchers due to its promising behavior as assisting technology for visually impaired *** technology is also helpful for the automatic data entry *** the proposed systemprepared a dataset of English language handwritten character *** proposed system has been trained for the large set of sample data and tested on the sample images of user-defined handwritten *** this research,multiple experiments get very worthy recognition *** proposed systemwill first performimage pre-processing stages to prepare data for training using a convolutional neural *** this processing,the input document is segmented using line,word and character *** proposed system get the accuracy during the character segmentation up to 86%.Then these segmented characters are sent to a convolutional neural network for their *** recognition and segmentation technique proposed in this paper is providing the most acceptable accurate results on a given *** proposed work approaches to the accuracy of the result during convolutional neural network training up to 93%,and for validation that accuracy slightly decreases with 90.42%.

关键词： Convolutional neural network segmentation skew cursive characters recognition

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Mengzhe Wang, Yali Wu, Jiaxi Wang, Yiru Li, Hanqing Li, Bo Gan, Weihao Wu, Wei Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China SenseTime Research University of Chinese Academy of Science China Shanghai AI Laboratory Shanghai China Beihang University China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance-level annotations in the target domain. Existing approaches mainly focus on either of these two difficulties, even though they are closely coupled in cross domain object detection. To solve this problem, we propose a novel Target-perceived Dual-branch Distillation (TDD) framework. By integrating detection branches of both source and target domains in a unified teacher-student learning scheme, it can reduce domain shift and generate reliable supervision effectively. In particular, we first introduce a distinct Target Proposal Perceiver between two domains. It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention. Afterwards, we design a concise Dual Branch Self Distillation strategy for model training, which can progressively integrate complementary object knowledge from different domains via self-distillation in two branches. Finally, we conduct extensive experiments on a number of widely-used scenarios in cross domain object detection. The results show that our TDD significantly outperforms the state-of-the-art methods on all the benchmarks. Our code and model will be available at here. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

Reproducible Abnormalities and Diagnostic Generalizability of White Matter in Alzheimer’s Disease

学校读者我要写书评

暂无评论

Neuroscience Bulletin 2023年第10期39卷 1533-1543页

作者： Yida Qu Pan Wang Hongxiang Yao Dawei Wang Chengyuan Song Hongwei Yang Zengqiang Zhang Pindong Chen Xiaopeng Kang Kai Du Lingzhong Fan Bo Zhou Tong Han Chunshui Yu Xi Zhang Nianming Zuo Tianzi Jiang Yuying Zhou Bing Liu Ying Han Jie Lu Yong Liu Multi-Center Alzheimer’s Disease Imaging(MCADI)Consortium Brainnetome Center and National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Department of Neurology Tianjin Huanhu HospitalTianjin UniversityTianjin 300222China Department of Radiology Department of Epidemiology and Health StatisticsSchool of Public HealthQilu Hospital of Shandong UniversityJi’nan 250063China Department of Neurology Qilu Hospital of Shandong UniversityJi’nan 250063China Department of Radiology Xuanwu Hospital of Capital Medical UniversityBeijing 100053China Branch of Chinese PLA General HospitalSanya 572022China Department of Neurology The Second Medical CentreNational Clinical Research Centre for Geriatric DiseasesChinese PLA General HospitalBeijing 100089China Department of Radiology Tianjin Huanhu HospitalTianjin 300222China Department of Radiology Tianjin Medical University General HospitalTianjin 300052China Department of Neurology Xuanwu Hospital of Capital Medical UniversityBeijing 100053China Beijing Institute of Geriatrics Beijing 100053China National Clinical Research Center for Geriatric Disorders Beijing 100053China Center of Alzheimer’s Disease Beijing Institute for Brain DisordersBeijing 100053China State Key Lab of Cognition Neuroscience&Learning Beijing Normal UniversityBeijing 100091China School of Artificial Intelligence Beijing University of Posts and TelecommunicationsBeijing 100876China 不详

Alzheimer’s disease(AD)is associated with the impairment of white matter(WM)*** current study aimed to verify the utility of WM as the neuroimaging marker of AD with multisite diffusion tensor imaging datasets[321 patients with AD,265 patients with mild cognitive impairment(MCI),279 normal controls(NC)],a unified pipeline,and independent site *** fiber quantification was used to extract diffusion profiles along ***-effects meta-analyses showed a reproducible degeneration pattern in which fractional anisotropy significantly decreased in the AD and MCI groups compared with *** learning models using tract-based features showed good generalizability among independent site *** diffusion metrics of the altered regions and the AD probability predicted by the models were highly correlated with cognitive ability in the AD and MCI *** highlighted the reproducibility and generalizability of the degeneration pattern of WM tracts in AD.

关键词： Alzheimer’s disease Diffusion tensor imaging White matter tracts Cross-validation

Focus on Content not Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN

学校读者我要写书评

暂无评论

Focus on Content not Noise: Improving Image Generation for N...

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Jonas Utz Tobias Weise Maja Schlereth Fabian Wagner Mareike Thies Mingxuan Gu Stefan Uderhardt Katharina Breininger Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Pattern Recognition Lab FAU Erlangen-Nürnberg Germany Department of Medicine 3 - Rheumatology and Immunology FAU Erlangen-Nürnberg Germany Deutsches Zentrum für Immuntherapie FAU Erlangen-Nürnberg Germany Exploratory Research Unit Optical Imaging Centre Erlangen FAU Erlangen-Nürnberg Germany

Annotating nuclei in microscopy images for the training of neural networks is a laborious task that requires expert knowledge and suffers from inter- and intra-rater variability, especially in fluorescence microscopy. Generative networks such as CycleGAN can inverse the process and generate synthetic microscopy images for a given mask, thereby building a synthetic dataset. However, past works report content inconsistencies between the mask and generated image, partially due to CycleGAN minimizing its loss by hiding shortcut information for the image reconstruction in high frequencies rather than encoding the desired image content and learning the target task. In this work, we propose to remove the hidden shortcut information, called steganography, from generated images by employing a low pass filtering based on the discrete cosine transform (DCT). We show that this increases coherence between generated images and cycled masks and evaluate synthetic datasets on a downstream nuclei segmentation task. Here we achieve an improvement of 5.4 percentage points in the F1-score compared to a vanilla CycleGAN. Integrating advanced regularization techniques into the CycleGAN architecture may help mitigate steganography-related issues and produce more accurate synthetic datasets for nuclei segmentation.

关键词：

Brain-Inspired Theory of Mind Spiking Neural Network Elevates Multi-Agent Cooperation and Competition

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zhao, Zhuoya Zhao, Feifei Zhao, Yuxuan Zeng, Yi Sun, Yinqian Brain-inspired Cognitive Intelligence Lab Institute of Automation Chinese Academy of Sciences Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China School of Future Technology University of Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

Theory of mind (ToM), a kind of high social cognitive ability, enables individuals to infer others’ mental states and thus explain and predict others’ behaviors. During dynamic social interaction, inferring and predicting others’ behaviors through ToM is crucial for obtaining more benefits in cooperative and competitive tasks. However, most existing multi-agent decision-making methods select behaviors based on agents’ observations, lacking in-depth inspiration from the ToM mechanism in the brain and thus limiting the performance of multi-agent decision-making. In this paper, we proposed a Multi-Agent Theory of Mind Spiking Neural Network (MAToM-SNN) model, which consists of a ToM model and a decision-making module. We designed two brain-inspired ToM modules (Self-ToM and Other-ToM) to predict others’ behavior based on self-experience and observations of others, respectively. Then, each agent will adjust its behavior according to the predicted actions of others. The proposed model has been verified in multi-agent decision-making environments with cooperative and competitive tasks. The experimental results show that introducing ToM and SNNs could improve cooperation efficiency and help achieve higher rewards compared to multi-agent reinforcement learning models. Especially for competitive tasks, the agents with ToM could improve the rewards of their team by predicting the actions of other agents. © 2022, The Authors. All rights reserved.

关键词： Neural networks

Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, Jinfan You, Zhiyuan Gu, Jinjin Zhu, Kaiwen Xue, Tianfan Dong, Chao Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China The Chinese University of Hong Kong 999077 Hong Kong The University of Sydney NSW2006 Australia Shanghai Jiao Tong University Shanghai200240 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Shenzhen University of Advanced Technology Shenzhen518055 China

Generalization remains a significant challenge for low-level vision models, which often struggle with unseen degradations in real-world scenarios despite their success in controlled benchmarks. In this paper, we revisit the generalization problem in low-level vision models. Image deraining is selected as a case study due to its well-defined and easily decoupled structure, allowing for more effective observation and analysis. Through comprehensive experiments, we reveal that the generalization issue is not primarily due to limited network capacity but rather the failure of existing training strategies, which lead networks to overfit specific degradation patterns. Our findings show that guiding networks to focus on learning the underlying image content, rather than the degradation patterns, is key to improving generalization. We demonstrate that balancing the complexity of background images and degradations in the training data helps networks better fit the image distribution. Furthermore, incorporating content priors from pre-trained generative models significantly enhances generalization. Experiments on both image deraining and image denoising validate the proposed strategies. We believe the insights and solutions will inspire further research and improve the generalization of low-level vision models. Copyright © 2025, The Authors. All rights reserved.

关键词： Image denoising

Focus on Content not Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Utz, Jonas Weise, Tobias Schlereth, Maja Wagner, Fabian Thies, Mareike Gu, Mingxuan Uderhardt, Stefan Breininger, Katharina Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Pattern Recognition Lab FAU Erlangen-Nürnberg Germany Department of Medicine 3 - Rheumatology and Immunology FAU Erlangen-Nürnberg Germany Deutsches Zentrum für Immuntherapie FAU Erlangen-Nürnberg Germany Exploratory Research Unit Optical Imaging Centre Erlangen FAU Erlangen-Nürnberg Germany

关键词： Fluorescence microscopy

MTVCrafter: 4D Motion Tokenization for Open-World Human Image Animation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ding, Yanbo Hu, Xirui Guo, Zhizhi Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China China Telecom China School of Computer Science and Technology Xi’an Jiaotong University China School of Artificial Intelligence University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China

Human image animation has gained increasing attention and developed rapidly due to its broad applications in digital humans. However, existing methods rely largely on 2D-rendered pose images for motion guidance, which limits generalization and discards essential 3D information for open-world animation. To tackle this problem, we propose MTVCrafter (Motion Tokenization Video Crafter), the first framework that directly models raw 3D motion sequences (i.e., 4D motion) for human image animation. Specifically, we introduce 4DMoT (4D motion tokenizer) to quantize 3D motion sequences into 4D motion tokens. Compared to 2D-rendered pose images, 4D motion tokens offer more robust spatio-temporal cues and avoid strict pixel-level alignment between pose image and character, enabling more flexible and disentangled control. Then, we introduce MV-DiT (Motion-aware Video DiT). By designing unique motion attention with 4D positional encodings, MV-DiT can effectively leverage motion tokens as 4D compact yet expressive context for human image animation in the complex 3D world. Hence, it marks a significant step forward in this field and opens a new direction for pose-guided human video generation. Experiments show that our MTVCrafter achieves state-of-the-art results with an FID-VID of 6.98, surpassing the second-best by 65%. Powered by robust motion tokens, MTVCrafter also generalizes well to diverse open-world characters (single/multiple, full/half-body) across various styles and scenarios. Our video demos and code are on: https://***/DINGYANB/MTVCrafter. Copyright © 2025, The Authors. All rights reserved.

关键词： Three dimensional computer graphics