检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Manufacturing and robotics, ICIMR 2024

作者： Zeng, Haotian Cong, Jiheng Hong, Hantong Yu, Zihan Zhang, Fan Li, Guojie School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou China School of Robotics Xi’an Jiaotong-Liverpool University Suzhou China Hebei University of Environmental Engineering Qinhuangdao China School of Electrical Engineering Electronics and Computer Science University of Liverpool Liverpool United Kingdom

ISBN: (纸本)9789819639489

Glaucoma is a leading cause of irreversible blindness, often worsened by delayed diagnosis. Traditional diagnostic methods have limitations in early detection and require significant expertise. Recent advancements in machine learning and deep learning have shown promise in enhancing the diagnostic accuracy and efficiency of glaucoma detection using fundus imagery. This study presents a four-stage method for glaucoma classification. Fundus images are processed using VGG16 and ViT for feature extraction, capturing both local and global features. These features are then fused and reduced in dimensionality using Principal Component Analysis. Finally, the reduced features are classified using a Random Forest classifier. The integrated feature fusion model demonstrates significant improvements in diagnostic performance, achieving higher accuracy, specificity, and sensitivity in distinguishing between non-referable and referable glaucoma classes compared to traditional methods. Specifically, our model achieved an accuracy of 94.2%, an F1 score of 94.2%, a sensitivity of 94.44%, and a specificity of 94.0%. The use of both CNNs and ViTs for feature extraction leverages their strengths, resulting in a more effective diagnostic tool. The combination of CNNs, ViTs, and Random Forest classifiers, along with advanced data augmentation techniques, shows substantial potential for early glaucoma detection and ongoing monitoring. This approach addresses the limitations of current machine learning models and enhances diagnostic accuracy and efficiency, making it a promising tool for clinical settings. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Driving Scene Understanding with Traffic Scene-Assisted Topology Graph Transformer 24

Driving Scene Understanding with Traffic Scene-Assisted Topo...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Rong, Fu Peng, Wenjin Lan, Meng Zhang, Qian Zhang, Lefei National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China Hong Kong University of Science and Technology Hong Kong Hong Kong Horizon Robotics Beijing China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Hubei Luojia Laboratory Wuhan China

ISBN: (纸本)9798400706868

Driving scene topology reasoning aims to understand the objects present in the current road scene and model their topology relationships to provide guidance information for downstream tasks. Previous approaches fail to adequately facilitate interactions among traffic objects and neglect to incorporate scene information into topology reasoning, thus limiting the comprehensive exploration of potential correlations among objects and diminishing the practical significance of the reasoning results. Besides, the lack of constraints on lane direction may introduce erroneous guidance information and lead to a decrease in topology prediction accuracy. In this paper, we propose a novel topology reasoning framework, dubbed TSTGT, to address these issues. Specifically, we design a divide-and-conquer topology graph Transformer to respectively infer the lane-lane and lane-traffic topology relationships, which can effectively aggregate the local and global object information in the driving scene and facilitate the topology relationship learning. Additionally, a traffic scene-assisted reasoning module is devised and combined with the topology graph Transformer to enhance the practical significance of lane-traffic topology. In terms of lane detection, we develop a point-wise matching strategy to infer lane centerlines with correct directions, thereby improving the topology reasoning accuracy. Extensive experimental results on Openlane-V2 benchmark validate the superiority of our TSTGT over state-of-the-art methods and the effectiveness of our proposed modules. The code is available at https://***/rongfu-dsb/TSTGT. © 2024 ACM.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face Anti-Spoofing 18

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face A...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Zhang, Ying Zhu, Xiangyu Liu, Ajian Lin, Xun Wan, Jun Zhang, Jing Lei, Zhen Beihang University School of Computer Science and Engineering China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation China University of Chinese Academy of Sciences School of Artificial Intelligence China Macau University of Science and Technology School of Computer Science and Engineering China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation China

ISBN: (纸本)9798350364132

Face anti-spoofing (FAS) is pivotal in safeguarding the integrity of face recognition systems. Flexible-modal FAS utilizes multi-modal data and trains a unified model adaptable to any single-modal testing scenario. This innovation addresses the shortcomings of conventional multi-modal FAS approaches, which typically demand separate model training and deployment for each modality. However, existing flexible-modal FAS approaches activate specific network branches based on the modality of the tested sample. This not only increases the model's parameters but also necessitates the provision of the image's modality for testing, thereby constraining deployment flexibility. To address the issue, we present Compound Prompt Learning CLIP (CPL-CLIP), a novel method for flexible-modal FAS. This approach capitalizes on a learned textual prompt that is nearly independent of modality, thus bolstering class-based classification across arbitrary modalities. Specifically, our CPL-CLIP introduces a Dual-Branch Prompt (DBP), consisting of class and modal prompts that describe and guide classification, where each prompt is composed of learnable vectors and fixed templates. To further render the class prompt as modality-agnostic as possible, a Cosine Similarity Loss (CSL) is proposed to facilitate the maximal separation of the class prompt from the modality prompt. With only the class prompt utilized during testing, CPL-CLIP enables deployment in diverse modal testing scenarios without the necessity of the test image's modality to be known. Extensive experiments demonstrate CPL-CLIP's superiority over existing methods on several flexible-modal FAS benchmarks. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

VIDA: HOMEOSTATIC VISUAL DOMAIN ADAPTER FOR CONTINUAL TEST TIME ADAPTATION 12

VIDA: HOMEOSTATIC VISUAL DOMAIN ADAPTER FOR CONTINUAL TEST T...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Liu, Jiaming Yang, Senqiao Jia, Peidong Zhang, Renrui Lu, Ming Guo, Yandong Xue, Wei Zhang, Shanghang National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China AI2Robotics China The Chinese University of Hong Kong Hong Kong Hong Kong University of Science and Technology Hong Kong

Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existing methods mainly focus on model-based adaptation, which aims to leverage a self-training manner to extract the target domain knowledge. However, pseudo labels can be noisy and the updated model parameters are unreliable under dynamic data distributions, leading to error accumulation and catastrophic forgetting in the continual adaptation process. To tackle these challenges and maintain the model plasticity, we design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Specifically, we first comprehensively explore the different domain representations of the adapters with trainable high-rank or low-rank embedding spaces. Then we inject ViDAs into the pre-trained model, which leverages high-rank and low-rank features to adapt the current domain distribution and maintain the continual domain-shared knowledge, respectively. To exploit the low-rank and high-rank ViDAs more effectively, we further propose a Homeostatic Knowledge Allotment (HKA) strategy, which adaptively combines different knowledge from each ViDA. Extensive experiments conducted on four widely used benchmarks demonstrate that our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks. Note that, our method can be regarded as a novel transfer paradigm for large-scale models, delivering promising results in adaptation to continually changing distributions. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

A Quality Diversity Study in EvoDevo Processes for Engineering Design 13

A Quality Diversity Study in EvoDevo Processes for Engineeri...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Buchanan, Edgar Hickinbotham, Simon Dubey, Rahul Friel, Imelda Colligan, Andrew Price, Mark Tyrrell, Andy M. School of Physics Engineering and Technology University of York Intelligent Systems & Robotics Research Group United Kingdom Missouri State University Computer Science United States School of Mechanical & Aerospace Engineering Queen's University Belfast United Kingdom

ISBN: (纸本)9798350308365

For a long time engineering design has relied on human engineers manually crafting and refining designs using their expertise and experience. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are employed to investigate a broader design space that may go beyond what human engineers have considered. Previous literature has demonstrated the use of quality and diversity (QD) algorithms in evolutionary approaches to drive the process to better quality solutions. This paper provides a study to understand the effects of using QD algorithms in EvoDevo processes for engineering design. This paper also analyses the impact of using different behavioural characterisations (BC) in the performance of the quality of the solutions found. The results demonstrate that quality and diversity algorithms can find better solutions than other EAs for engineering design problems. It was also found that the characterisation of the BC is important to get the best results. © 2024 IEEE.

关键词： evodevo generative design neural networks quality diversity structural engineering

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 38

DeTrack: In-model Latent Denoising Learning for Visual Objec...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

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：

来源：评论

学校读者我要写书评

暂无评论

Visual-Language Collaborative Representation Network for Broad-Domain Few-Shot Image Classification 24

Visual-Language Collaborative Representation Network for Bro...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Guo, Qianyu Ren, Jieji Wang, Haofen Wu, Tianxing Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China College of Design and Innovation Tongji University Shanghai China School of Computer Science and Engineering Southeast University Nanjing China School of Computer Science Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

ISBN: (纸本)9798400706868

Visual-language models based on CLIP have shown remarkable abilities in general few-shot image classification. However, their performance drops in specialized fields such as healthcare or agriculture, because CLIP's pre-training does not cover all category data. Existing methods excessively depend on the multi-modal information representation and alignment capabilities acquired from CLIP pre-training, which hinders accurate generalization to unfamiliar domains. To address this issue, this paper introduces a novel visual-language collaborative representation network (MCRNet), aiming at acquiring a generalized capability for collaborative fusion and representation of multi-modal information. Specifically, MCRNet learns to generate relational matrices from an information fusion perspective to acquire aligned multi-modal features. This relationship generation strategy is category-agnostic, so it can be generalized to new domains. A class-adaptive fine-tuning inference technique is also introduced to help MCRNet efficiently learn alignment knowledge for new categories using limited data. Additionally, the paper establishes a new broad-domain few-shot image classification benchmark containing seven evaluation datasets from five domains. Comparative experiments demonstrate that MCRNet outperforms current state-of-the-art models, achieving an average improvement of 13.06% and 13.73% in the 1-shot and 5-shot settings, highlighting the superior performance and applicability of MCRNet across various domains. © 2024 ACM.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Happy: A Debiased Learning Framework for Continual Generalized Category Discovery 38

Happy: A Debiased Learning Framework for Continual Generaliz...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ma, Shijie Zhu, Fei Zhong, Zhun Liu, Wenzhuo Zhang, Xu-Yao Liu, Cheng-Lin MAIS Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Centre for Artificial Intelligence and Robotics HKISI-CAS China School of Computer Science and Information Engineering Hefei University of Technology China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom

Constantly discovering novel concepts is crucial in evolving environments. This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD), which aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. Although several settings are proposed to study the C-GCD task, they have limitations that do not reflect real-world scenarios. We thus study a more practical C-GCD setting, which includes more new classes to be discovered over a longer period, without storing samples of past classes. In C-GCD, the model is initially trained on labeled data of known classes, followed by multiple incremental stages where the model is fed with unlabeled data containing both old and new classes. The core challenge involves two conflicting objectives: discover new classes and prevent forgetting old ones. We delve into the conflicts and identify that models are susceptible to prediction bias and hardness bias. To address these issues, we introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization. For the prediction bias, we first introduce clustering-guided initialization to provide robust features. In addition, we propose soft entropy regularization to assign appropriate probabilities to new classes, which can significantly enhance the clustering performance of new classes. For the harness bias, we present the hardness-aware prototype sampling, which can effectively reduce the forgetting issue for previously seen classes, especially for difficult classes. Experimental results demonstrate our method proficiently manages the conflicts of C-GCD and achieves remarkable performance across various datasets, e.g., 7.5% overall gains on ImageNet-100. Our code is publicly available at https://***/mashijie1028/Happy-CGCD. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

REMOTELY CONTROLLABLE DNA MICROFLOW 26

REMOTELY CONTROLLABLE DNA MICROFLOW

引用

26th International Conference on Miniaturized Systems for Chemistry and Life sciences, MicroTAS 2022

作者： Udono, Hirotake Nomura, Shin-Ichiro M. Takinoue, Masahiro Department of Computer Science School of Computing Tokyo Institute of Technology Japan Department of Robotics Graduate School of Engineering Tohoku University Japan

ISBN: (纸本)9781733419048

Despite an emerging interest in fluid manipulation within confined environment such as biological cells and micro-scale biomimics, remotely controllable micro-scale flow remains unexplored. However, intracellular microfluidics is not compatible with established top-down microfluidic methods because of limited accessibility. Here, we demonstrate photoresponsive DNA fluid, condensate of DNA nanostructures (DNA motifs), as a versatile mechanistic tool for the remote control of microflow. Insertion site of azobenzene, introduced for photocontrollability, determines an extent of dynamic shift in binding enthalpy between DNA motifs, providing the underpinning mechanism for drastic and facile flow-mode switching. © 2022 MicroTAS 2022 - 26th International Conference on Miniaturized Systems for Chemistry and Life sciences. All rights reserved.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Laser-scribed graphene for sensors:preparation,modification,applications,and future prospects

引用

Light(Advanced Manufacturing) 2023年第2期4卷 67-91页

作者： Xing Liu Fangyi Zhang Qiwen Zhang Zhengfen Wan Xi Chen Institute of Photonic Chips University of Shanghai for Science and TechnologyShanghai 200093China Centre for Artificial-Intelligence Nanophotonics School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Queensland University of Technology(QUT)Centre for Robotics BrisbaneQLD 4000Australia

Sensors are widely used to acquire biological and environmental information for medical diagnosis,and health and environmental *** is a promising new sensor material that has been widely used in sensor fabrication in recent *** with many other existing graphene preparation methods,laser-scribed graphene(LSG)is simple,low-cost,environmentally friendly,and has good conductivity and high thermal stability,making it widely used in the sensor *** paper summarizes existing LSG methods for sensor *** LSG preparation methods and their variants are introduced first,followed by a summary of LSG modification methods designed explicitly for sensor ***,the applications of LSG in stress,bio,gas,temperature,and humidity sensors are summarized with a particular focus on multifunctional integrated ***,the current challenges and prospects of LSG-based sensors are discussed.

关键词： Graphene Graphene oxide Laser-scribed graphene Sensors

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：