检索结果-内蒙古大学图书馆

Calibration-Free Raw Image Denoising via Fine-Grained Noise Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5368-5384页

作者： Yunhao Zou Ying Fu Yulun Zhang Tao Zhang Chenggang Yan Radu Timofte Beijing Laboratory of Intelligent Information Technology School of Computer Science and Technology Beijing Institute of Technology Beijing China MIIT Key Laboratory of Complex-field Intelligent Exploration Beijing Institute of Technology Beijing China Shanghai Jiao Tong University Shanghai China School of Communication Engineering Hangzhou Dianzi University Hangzhou China Lishui Institute of Hangzhou Dianzi University Lishui China Computer Vision Lab IFI and CAIDAS University of Würzburg Würzburg Germany

Image denoising has progressed significantly due to the development of effective deep denoisers. To improve the performance in real-world scenarios, recent trends prefer to formulate superior noise models to generate realistic training data, or estimate noise levels to steer non-blind denoisers. In this paper, we bridge both strategies by presenting an innovative noise estimation and realistic noise synthesis pipeline. Specifically, we integrates a fine-grained statistical noise model and contrastive learning strategy, with a unique data augmentation to enhance learning ability. Then, we use this model to estimate noise parameters on evaluation dataset, which are subsequently used to craft camera-specific noise distribution and synthesize realistic noise. One distinguishing feature of our methodology is its adaptability: our pre-trained model can directly estimate unknown cameras, making it possible to unfamiliar sensor noise modeling using only testing images, without calibration frames or paired training data. Another highlight is our attempt in estimating parameters for fine-grained noise models, which extends the applicability to even more challenging low-light conditions. Through empirical testing, our calibration-free pipeline demonstrates effectiveness in both normal and low-light scenarios, further solidifying its utility in real-world noise synthesis and denoising tasks.

关键词： Noise Data models Pipelines Estimation Noise reduction Image denoising Training Noise measurement Adaptation models Cameras

来源：评论

学校读者我要写书评

暂无评论

Hardware-Agnostic Behavior Trees:Towards Generic Robot Behavior Design

SSRN

引用

SSRN 2022年

作者： El-Ariss, Wafic Daher, Naseem Elhajj, Imad H. Logistics Robotics BMW Group Petuelring 130 Munich80809 Germany Vision and Robotics Lab Department of Mechanical Engineering American University of Beirut Riad El-Solh Beirut1107 Lebanon Vision and Robotics Lab Department of Electrical and Computer Engineering American University of Beirut Riad El-Solh Beirut1107 Lebanon

Decision-Making (DM) algorithms are an essential component of autonomous agents that control the behavior of Non-Player Characters (NPCs) in computer games, as well as the behavior of autonomous robots. Behavior Trees (BTs) have gained significant traction in recent years for having facilitated the development of complex behaviors for autonomous robots and NPCs, by offering a simple, yet powerful, task-switching architecture that relies on composing modular and reusable unit behaviors to achieve the overall desired *** is well understood how to design BT leaves, the unit behavior of BTs, for them to be reused across the behavior of a single robot system, however, there is a need for these leaves to generalize across systems of differing hardware, thus achieving hardware abstraction, and producing what we call Hardware-Agnostic Behavior Tree Leaves that would reduce the development time and costs of new *** this paper, we address this goal by first presenting a new formulation for BTs that incorporates parameterization. Subsequently, we propose a method to specify DM behaviors in a hardware-agnostic manner. Then, we apply object-oriented design methods to specify BTs. We combine the three techniques to define Hardware-Agnostic Behavior Tree Leaves , and propose a method to design them so that these unit behaviors can be reused across systems of differing hardware. We demonstrate the applicability of our proposed method by designing a completely hardware-agnostic, and thus reusable, BT software that we then apply on two real robotic systems with differing hardware used at the BMW Group, and we show that the BT software developed using our methods leads to higher reusability (as per Chidamber and Kemerer metrics) by conducting a comparison against a benchmark BT software built using state-of-the-art methods. Four out of the five used Chidamber and Kemerer metrics indicated that our method increased reusability, it resulted in software that is 7.7% shorter

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

FM-FCN:A Neural Network with Filtering Modules for Accurate Vital Signs Extraction

引用

Research 2025年第1期2024卷 92-106页

作者： Fangfang Zhu Qichao Niu Xiang Li Qi Zhao Honghong Su Jianwei Shuai Department of Physics and Fujian Provincial Key Laboratory for Soft Functional Materials ResearchXiamen UniversityXiamen 361005China National Institute for Data Science in Health and Medicine and State Key Laboratory of Cellular Stress BiologyInnovation Center for Cell Signaling NetworkXiamen UniversityXiamen 361005China Vitalsilicon Technology Co.Ltd. JiaxingZhejiang 314006China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan 114051China Yangtze Delta Region Institute of Tsinghua University ZhejiangJiaxing 314006China Wenzhou Institute University of Chinese Academy of SciencesWenzhou 325001China Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine Vision and Brain Health)Wenzhou 325001China

Neural networks excel at capturing local spatial patterns through convolutional modules,but they may struggle to identify and effectively utilize the morphological and amplitude periodic nature of physiological *** this work,we propose a novel network named filtering module fully convolutional network(FM-FCN),which fuses traditional filtering techniques with neural networks to amplify physiological signals and suppress ***,instead of using a fully connected layer,we use an FCN to preserve the time-dimensional correlation information of physiological signals,enabling multiple cycles of signals in the network and providing a basis for signal ***,we introduce the FM as a network module that adapts to eliminate unwanted interference,leveraging the structure of the *** approach builds a bridge between deep learning and signal processing ***,we evaluate the performance of FM-FCN using remote *** results demonstrate that FM-FCN outperforms the second-ranked method in terms of both blood volume pulse(BVP)signal and heart rate(HR)*** substantially improves the quality of BVP waveform reconstruction,with a decrease of 20.23%in mean absolute error(MAE)and an increase of 79.95%in signal-to-noise ratio(SNR).Regarding HR estimation accuracy,FM-FCN achieves a decrease of 35.85%in MAE,29.65%in error standard deviation,and 32.88%decrease in 95%limits of agreement width,meeting clinical standards for HR accuracy *** results highlight its potential in improving the accuracy and reliability of vital sign measurement through high-quality BVP signal *** codes and datasets are available online at https://***/zhaoqi106/FM-FCN.

关键词： physiological signalsin filtering module fully convolutional network fm fcn which vital signs extraction amplify physiological signals convolutional modulesbut neural networks filtering module capturing local spatial patterns

来源：评论

学校读者我要写书评

暂无评论

CC-DCNet: Dynamic Convolutional Neural Network with Contrastive Constraints for Identifying Lung Cancer Subtypes on Multi-modality Images

arXiv

引用

arXiv 2024年

作者： Jin, Yuan Ma, Gege Chen, Geng Lyu, Tianling Egger, Jan Lyu, Junhui Zhang, Shaoting Zhu, Wentao Zhejiang Lab 311121 China Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi’an710072 China The Zhejiang University School of Medicine Sir Run Run Shaw Hospital Hangzhou310016 China Shanghai Artificial Intelligence Laboratory Shanghai200120 China

The accurate diagnosis of pathological subtypes of lung cancer is of paramount importance for follow-up treatments and prognosis managements. Assessment methods utilizing deep learning technologies have introduced novel approaches for clinical diagnosis. However, the majority of existing models rely solely on single-modality image input, leading to limited diagnostic accuracy. To this end, we propose a novel deep learning network designed to accurately classify lung cancer subtype with multi-dimensional and multi-modality images, i.e., CT and pathological images. The strength of the proposed model lies in its ability to dynamically process both paired CT-pathological image sets as well as independent CT image sets, and consequently optimize the pathology-related feature extractions from CT images. This adaptive learning approach enhances the flexibility in processing multi-dimensional and multi-modality datasets and results in performance elevating in the model testing phase. We also develop a contrastive constraint module, which quantitatively maps the cross-modality associations through network training, and thereby helps to explore the "gold standard" pathological information from the corresponding CT scans. To evaluate the effectiveness, adaptability, and generalization ability of our model, we conducted extensive experiments on a large-scale multi-center dataset and compared our model with a series of state-of-the-art classification models. The experimental results demonstrated the superiority of our model for lung cancer subtype classification, showcasing significant improvements in accuracy metrics such as ACC, AUC, and F1-score. Copyright © 2024, The Authors. All rights reserved.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Dataset Condensation via Efficient Synthetic-Data Parameterization

arXiv

引用

arXiv 2022年

作者： Kim, Jang-Hyun Kim, Jinuk Oh, Seong Joon Yun, Sangdoo Song, Hwanjun Jeong, Joonhyun Ha, Jung-Woo Song, Hyun Oh Department of Computer Science and Engineering Seoul National University Korea Republic of NAVER AI Lab Korea Republic of University of Tübingen Germany Image Vision NAVER Clova

The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning. Recent studies on dataset condensation attempt to reduce the dependence on such massive data by synthesizing a compact training dataset. However, the existing approaches have fundamental limitations in optimization due to the limited representability of synthetic datasets without considering any data regularity characteristics. To this end, we propose a novel condensation framework that generates multiple synthetic data with a limited storage budget via efficient parameterization considering data regularity. We further analyze the shortcomings of the existing gradient matching-based condensation methods and develop an effective optimization technique for improving the condensation of training data information. We propose a unified algorithm that drastically improves the quality of condensed data against the current state-of-the-art on CIFAR-10, ImageNet, and Speech Commands. Copyright © 2022, The Authors. All rights reserved.

关键词： Condensation

来源：评论

学校读者我要写书评

暂无评论

Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps 38

Binding in hippocampal-entorhinal circuits enables compositi...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kymn, Christopher J. Mazelet, Sonia Thomas, Anthony Kleyko, Denis Frady, E. Paxon Sommer, Friedrich T. Olshausen, Bruno A. Redwood Center for Theoretical Neuroscience Helen Wills Neuroscience Institute UC Berkeley Berkeley United States Université Paris-Saclay ENS Paris-Saclay Gif-sur-Yvette France Department of Electrical and Computer Engineering UC Davis Davis United States Centre for Applied Autonomous Sensor Systems Örebro University Örebro Sweden Intelligent Systems Lab Research Institutes of Sweden Kista Sweden Intel Labs Santa Clara United States Herbert Wertheim School of Optometry & Vision Science UC Berkeley Berkeley United States

We propose a normative model for spatial representation in the hippocampal formation that combines optimality principles, such as maximizing coding range and spatial information per neuron, with an algebraic framework for computing in distributed representation. Spatial position is encoded in a residue number system, with individual residues represented by high-dimensional, complex-valued vectors. These are composed into a single vector representing position by a similarity-preserving, conjunctive vector-binding operation. Self-consistency between the representations of the overall position and of the individual residues is enforced by a modular attractor network whose modules correspond to the grid cell modules in entorhinal cortex. The vector binding operation can also associate different contexts to spatial representations, yielding a model for entorhinal cortex and hippocampus. We show that the model achieves normative desiderata including superlinear scaling of patterns with dimension, robust error correction, and hexagonal, carry-free encoding of spatial position. These properties in turn enable robust path integration and association with sensory inputs. More generally, the model formalizes how compositional computations could occur in the hippocampal formation and leads to testable experimental predictions. © 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

RGB-D Indiscernible Object Counting in Underwater Scenes

arXiv

引用

arXiv 2023年

作者： Sun, Guolei Cheng, Xiaogang An, Zhaochong Wang, Xiaokang Liu, Yun Fan, Deng-Ping Cheng, Ming-Ming Gool, Luc Van Computer Vision Lab ETH Zurich Zurich8092 Switzerland Pioneer Centre for Artificial Intelligence University of Copenhagen Copenhagen1350 Denmark School of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Jiangsu Province Nanjing210003 China College of Computer Science Nankai University Tianjin300350 China

Recently, indiscernible/camouflaged scene understanding has attracted lots of research attention in the vision community. We further advance the frontier of this field by systematically studying a new challenge named indiscernible object counting (IOC), the goal of which is to count objects that are blended with respect to their surroundings. Due to a lack of appropriate IOC datasets, we present a large-scale dataset IOCfish5K which contains a total of 5,637 high-resolution images and 659,024 annotated center points. Our dataset consists of a large number of indiscernible objects (mainly fish) in underwater scenes, making the annotation process all the more challenging. IOCfish5K is superior to existing datasets with indiscernible scenes because of its larger scale, higher image resolutions, more annotations, and denser scenes. All these aspects make it the most challenging dataset for IOC so far, supporting progress in this area. Benefiting from the recent advancements of depth estimation foundation models, we construct high-quality depth maps for IOCfish5K by generating pseudo labels using the Depth Anything V2 model. The RGB-D version of IOCfish5K is named IOCfish5KD. For benchmarking purposes on IOCfish5K, we select 14 mainstream methods for object counting and carefully evaluate them. For multimodal IOCfish5K-D, we evaluate other 4 popular multimodal counting methods. Furthermore, we propose IOCFormer, a new strong baseline that combines density and regression branches in a unified framework and can effectively tackle object counting under concealed scenes. We also propose IOCFormer-D to enable the effective usage of depth modality in helping detect and count objects hidden in their environments. Experiments show that IOCFormer and IOCFormer-D achieve state-of-the-art scores on IOCfish5K and IOCfish5K-D, respectively. The resources are publicly available at ***/GuoleiSun/Indiscernible-Object-Counting. Copyright © 2023, The Authors. All rights reserved.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

AffectiveNet: Affective-motion feature learning for micro expression recognition

arXiv

引用

arXiv 2021年

作者： Verma, Monu Vipparthi, Santosh Kumar Singh, Girdhari Vision Intelligence Lab Department of Computer Science and Engineering Malaviya National Institute of Technology Jaipur India

Micro-expressions are hard to spot due to fleeting and involuntary moments of facial muscles. Interpretation of micro emotions from video clips is a challenging task. In this paper we propose an affective-motion imaging that cumulates rapid and short-lived variational information of micro expressions into a single response. Moreover, we have proposed an AffectiveNet: affective-motion feature learning network that can perceive subtle changes and learns the most discriminative dynamic features to describe the emotion classes. The AffectiveNet holds two blocks: MICRoFeat and MFL block. MICRoFeat block conserves the scale-invariant features, which allows network to capture both coarse and tiny edge variations. While MFL block learns micro-level dynamic variations from two different intermediate convolutional layers. Effectiveness of the proposed network is tested over four datasets by using two experimental setups: person independent (PI) and cross dataset (CD) validation. The experimental results of the proposed network outperforms the state-of-the-art approaches with significant margin for MER approaches. © 2021, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT ONLINE labEL CONSISTENT HASHING FOR LARGE-SCALE CROSS-MODAL RETRIEVAL

EFFICIENT ONLINE LABEL CONSISTENT HASHING FOR LARGE-SCALE CR...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Yi, Jinhan Liu, Xin Cheung, Yiu-Ming Xu, Xing Fan, Wentao He, Yi Department of Computer Science and Technology Huaqiao University Xiamen361021 China Xiamen Key Lab. of Computer Vision and Pattern Recognition Fujian Key Lab. of Big Data Intelligence and Security China Department of Computer Science Hong Kong Baptist University Kowloon Hong Kong School of Computer Science and Engineering University of Electronic Science and Technology of China China Provincial Key Laboratory for Computer Information Processing Technology Soochow University China

ISBN: (纸本)9781665438643

Existing cross-modal hashing still faces three challenges: (1) Most batch-based methods are unsuitable for processing large-scale and streaming data. (2) Current online methods often suffer from insufficient semantic association, while lacking flexibility to learn the hash functions for varying streaming data. (3) Existing supervised methods always require much computation time or accumulate large quantization loss to learn hash codes. To address above challenges, we present an efficient Online label Consistent Hashing (OLCH) for cross-modal retrieval, which aims to incrementally learn hash codes for the current arriving data, while updating the hash functions at a streaming manner. To be specific, an online semantic representation learning framework is designed to adaptively preserve the semantic similarity across different modalities, and a mini-batch online gradient descent approach associated with forward-backward splitting is developed to optimize the hash functions. Accordingly, the hash codes are adaptively learned online with the high discriminative capability, while avoiding high computation complexity to process the streaming data. Experimental results show its outstanding performance in comparison with the-state-of-arts. © 2021 IEEE computer Society. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

Robin: A Novel Method to Produce Robust Interpreters for Dee...

引用

IEEE International Conference on Automated Software engineering (ASE)

作者： Zhen Li Ruqian Zhang Deqing Zou Ning Wang Yating Li Shouhuai Xu Chen Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security Department of Computer Science University of Colorado Colorado Springs USA Center for Research in Computer Vision University of Central Florida USA School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA.

关键词：

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：