检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Elbatel, Marawan Martí, Robert Li, Xiaomeng The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The Computer Vision and Robotics Institute University of Girona Spain The Department of Electronic and Computer Engineering the Hong Kong University of Science and Technology Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Futian Shenzhen China

Representational transfer from publicly available models is a promising technique for improving medical image classification, especially in long-tailed datasets with rare diseases. However, existing methods often overlook the frequency-dependent behavior of these models, thereby limiting their effectiveness in transferring representations and generalizations to rare diseases. In this paper, we propose FoPro-KD, a novel framework that leverages the power of frequency patterns learned from frozen pretrained models to enhance their transferability and compression, presenting a few unique insights: 1) We demonstrate that leveraging representations from publicly available pre-trained models can substantially improve performance, specifically for rare classes, even when utilizing representations from a smaller pre-trained model. 2) We observe that pre-trained models exhibit frequency preferences, which we explore using our proposed Fourier Prompt Generator (FPG), allowing us to manipulate specific frequencies in the input image, enhancing the discriminative representational transfer. 3) By amplifying or diminishing these frequencies in the input image, we enable Effective Knowledge Distillation (EKD). EKD facilitates the transfer of knowledge from pre-trained models to smaller models. Through extensive experiments in long-tailed gastrointestinal image recognition and skin lesion classification, where rare diseases are prevalent, our FoPro-KD framework outperforms existing methods, enabling more accessible medical models for rare disease classification. Code is available at https://***/xmed-lab/FoPro-KD. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition

arXiv

引用

arXiv 2023年

作者： Dhiaf, Marwa Souibgui, Mohamed Ali Wang, Kai Liu, Yuyang Kessentini, Yousri Fornés, Alicia Rouhou, Ahmed Cheikh InstaDeep United Kingdom Computer Vision Center UAB Spain Digital Research Center of Sfax SM@RTS Tunisia State Key Laboratory of Robotics China Shenyang Institute of Automation Chinese Academy of Sciences China

Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, i.e. when data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance in English, Italian, and Russian, whilst adding only a few parameters per task. The code and trained models will be publicly available1 © 2023, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity

arXiv

引用

arXiv 2022年

作者： Luo, Cheng Lin, Qinliang Xie, Weicheng Wu, Bizhu Xie, Jinheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University2Shenzhen Institute of Artificial Intelligence & Robotics for Society3Guangdong Key Laboratory of Intelligent Information Processing

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they rely on a classification layer with a closed set of categories. Furthermore, the perturbations generated by these methods may appear in regions easily perceptible to the human visual system (HVS). To circumvent the former problem, we propose a novel algorithm that attacks semantic similarity on feature representations. In this way, we are able to fool classifiers without limiting attacks to a specific dataset. For imperceptibility, we introduce the low-frequency constraint to limit perturbations within high-frequency components, ensuring perceptual similarity between adversarial examples and originals. Extensive experiments on three datasets (CIFAR-10, CIFAR-100, and ImageNet-1K) and three public online platforms indicate that our attack can yield misleading and transferable adversarial examples across architectures and datasets. Additionally, visualization results and quantitative performance (in terms of four different metrics) show that the proposed algorithm generates more imperceptible perturbations than the state-of-the-art methods. Code is made available at https://***/LinQinLiang/SSAH-adversarial-attack. © 2022, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Imaging for Identifying Foreign Objects on Pork Belly

arXiv

引用

arXiv 2025年

作者： Ghimpeteanu, Gabriela Rajani, Hayat Quintana, Josep Garcia, Rafael Coronis Computing SL University of Girona Science and Technology Park Carrer Pic de Peguera 11 Edifici Giroemprèn Girona17003 Spain Computer Vision and Robotics Research Institute University of Girona Campus Montilivi Edifici P4 Girona17003 Spain

Ensuring food safety and quality is critical in the food processing industry, where the detection of contaminants remains a persistent challenge. This study presents an automated solution for detecting foreign objects on pork belly meat using hyperspectral imaging (HSI). A hyperspectral camera was used to capture data across various bands in the near-infrared (NIR) spectrum (900-1700 nm), enabling accurate identification of contaminants that are often undetectable through traditional visual inspection methods. The proposed solution combines pre-processing techniques with a segmentation approach based on a lightweight vision Transformer (ViT) to distinguish contaminants from meat, fat, and conveyor belt materials. The adopted strategy demonstrates high detection accuracy and training efficiency, while also addressing key industrial challenges such as inherent noise, temperature variations, and spectral similarity between contaminants and pork belly. Experimental results validate the effectiveness of hyperspectral imaging in enhancing food safety, highlighting its potential for broad real-time applications in automated quality control processes. © 2025, CC BY-NC-SA.

关键词： Belt conveyors

来源：评论

学校读者我要写书评

暂无评论

Maize EfficientNet Fusion: Advancing Maize Disease Detection with MF-NET

Maize EfficientNet Fusion: Advancing Maize Disease Detection...

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Fatima Khalid Muhammad Hanif Qurat Ul Ain Faculty of Computer Science and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences and Engineering Topi KPK Pakistan Aerial Robotics and Vision Lab Ghulam Ishaq Khan Institute of Engineering Sciences and Engineering Topi KPK Pakistan Department of Computing Shifa Tameer-E-Millat University Islamabad Pakistan

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Maize is a vital global crop, essential for food security but highly susceptible to diseases that threaten yield and quality. Traditional methods for detecting these diseases are computationally intensive and rely on high-quality images, limiting their practical use in diverse field conditions. This research addresses these challenges by proposing MF-Net, a novel model that leverages two EfficientNet-b0 architectures with ReLU and Swish activation functions. Our approach involves partially training Model R with frozen early layers using ReLU, and fully training Model S with Swish activation for enhanced optimization and robustness. We employ model concatenation and feature fusion techniques to create a lightweight yet powerful model, complemented by additional layers for improved feature extraction and regularization. Experimental results on the Corn Disease and Severity (CD&S) dataset are compelling: MF-Net achieves a remarkable 95.7% accuracy and 96% precision in disease classification, and 88.3% accuracy and 88.46% precision in severity level detection. These results highlight the model's effectiveness under challenging conditions such as cluttered backgrounds and variable lighting, significantly reducing computation time without compromising accuracy. Hence, MF-Net presents an innovative and efficient solution for maize disease detection and severity assessment, offering significant advancements for agricultural practices and crop management.

关键词： Training Adaptation models Accuracy Computational modeling Crops Lighting computer architecture Feature extraction Robustness Diseases

来源：评论

学校读者我要写书评

暂无评论

UniTSFace: unified threshold integrated sample-to-sample loss for face recognition 23

UniTSFace: unified threshold integrated sample-to-sample los...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Qiufu Li Xi Jia Jiancan Zhou Linlin Shen Jinming Duan National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and School of Computer Science University of Birmingham UK National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China and Computer Vision Institute Shenzhen University China and Aqara Lumi United Technology Co. Ltd China School of Computer Science University of Birmingham UK and Alan Turing Institute UK

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

arXiv

引用

arXiv 2022年

作者： Xing, Hao Burschka, Darius Technical University of Munich Machine Vision and Perception Group Munich Institute of Robotics and Machine Intelligence Department of Computer Science Parkring 13 Munich85748 Germany

In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most existing Graph Convolutional Networks, the local attention mask is defined based on natural connections of human skeleton joints and ignores the dynamic relations for example between head, hands and feet joints. In addition, the attention mechanism has been proven effective in Natural Language Processing and image description, which is rarely investigated in existing methods. In this work, we proposed a new adaptive spatial attention layer that extends local attention map to global based on relative distance and relative angle information. Moreover, we design a new initial graph adjacency matrix that connects head, hands and feet, which shows visible improvement in terms of action recognition accuracy. The proposed model is evaluated on two large-scale and challenging datasets in the field of human activities in daily life: NTU-RGB+D and Kinetics skeleton. The results demonstrate that our model has strong performance on both dataset. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition

arXiv

引用

arXiv 2022年

作者： Luo, Cheng Song, Siyang Xie, Weicheng Shen, Linlin Gunes, Hatice Computer Vision Institute Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing China Department of Computer Science and Technology University of Cambridge United Kingdom

The activations of Facial Action Units (AUs) mutually influence one another. While the relationship between a pair of AUs can be complex and unique, existing approaches fail to specifically and explicitly represent such cues for each pair of AUs in each facial display. This paper proposes an AU relationship modelling approach that deep learns a unique graph to explicitly describe the relationship between each pair of AUs of the target facial display. Our approach first encodes each AU’s activation status and its association with other AUs into a node feature. Then, it learns a pair of multi-dimensional edge features to describe multiple task-specific relationship cues between each pair of AUs. During both node and edge feature learning, our approach also considers the influence of the unique facial display on AUs’ relationship by taking the full face representation as an input. Experimental results on BP4D and DISFA datasets show that both node and edge feature learning modules provide large performance improvements for CNN and transformer-based backbones, with our best systems achieving the state-of-the-art AU recognition results. Our approach not only has a strong capability in modelling relationship cues for AU recognition but also can be easily incorporated into various backbones. Our PyTorch code is made available at https://***/CVI-SZU/ME-GraphAU. Copyright © 2022, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Analytical Estimation of Interaction Force and its Application Point for Collaborative Robots

引用

IFAC-PapersOnLine 2022年第10期55卷 2451-2456页

作者： Dmitry Popov Alexandr Klimchik Anatol Pashkevich Institute of Robotics and Computer Vision Innopolis University Innopolis Russia IMT-Atlantique Nantes Nantes France Laboratoire des Sciences du Numérique de Nantes (LS2N) Nantes France

The paper deals with parameters estimation in the human-robot collaboration scenario. It presents an analytical algorithm for computing of the interaction force and its application point using measurement data obtained from the internal joint torque sensors only. The proposed algorithm is based on a specific extension of static equilibrium equations allowing to find the desired interaction force and action line. Further, this general solution is combined with geometric constraints describing manipulator surfaces and corresponding friction cones. Particular attention is paid to singular cases arising when the interaction force action line intersects one or several joint sensor axes. The developed technique was carefully evaluated via the simulation study.

关键词： robotics in manufacturing Human-Automation Integration Collaborative robots Human-robot interaction collaboration cooperation

来源：评论

学校读者我要写书评

暂无评论

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

arXiv

引用

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

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：