检索结果-内蒙古大学图书馆

Unsupervised Domain-Adaptive Semantic Segmentation for Surgical Instruments Leveraging Dropout-Enhanced Dual Heads and Coarse-Grained Classification Branch

IEEE Transactions on Medical Robotics and Bionics

引用

IEEE Transactions on Medical Robotics and Bionics 2025年

作者： Li, Ziqian Wang, Zhengyu Xu, Xinzhou Chen, Yongfa Schuller, Bjorn W. Hefei University of Technology School of Mechanical Engineering Hefei China Nanjing University of Posts and Telecommunications School of Internet of Things Nanjing China Graz University of Technology Signal Processing and Speech Communication Laboratory Graz Austria Chair of Health Informatics Munich Germany Munich Data Science Institute Munich Germany Munich Center for Machine Learning Munich Germany Imperial College London GLAM – the Group on Language Audio and Music London United Kingdom

Accurate semantic segmentation for surgical instruments is crucial in robot-assisted minimally invasive surgery, mainly regarded as a core module in surgical-instrument tracking and operation guidance. Nevertheless, it is usually difficult for existing semantic surgical-instrument segmentation approaches to adapt to unknown surgical scenes, particularly due to their insufficient consideration for reducing the domain gaps across different scenes. To address this issue, we propose an unsupervised domain-adaptive semantic segmentation approach for surgical instruments, leveraging Dropout-enhanced Dual Heads and Coarse-Grained classification branch (D2HCG). The proposed approach comprises dropout-enhanced dual heads for diverse feature representation, and a coarse-grained classification branch for capturing complexities across varying granularities. This incorporates consistency loss functions targeting fine-grained features and coarse-grained granularities, aiming to reduce crossscene domain gaps. Afterwards, we perform experiments in crossscene surgical-instrument semantic segmentation cases, with the experimental results reporting the effectiveness for the proposed approach, compared with state-of-the-art semantic segmentation ones. © 2018 IEEE.

关键词： coarse-grained classification dropout enhancement Surgical instruments unsupervised domain-adaptive semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Kernel based quantum machine learning at record rate: Many-body distribution functionals as compact representations

arXiv

引用

arXiv 2023年

作者： Khan, Danish Heinen, Stefan von Lilienfeld, O. Anatole Department of Chemistry University of Toronto St. George Campus TorontoON Canada Vector Institute for Artificial Intelligence TorontoONM5S 1M1 Canada Departments of Chemistry Materials Science and Engineering and Physics University of Toronto St. George Campus TorontoON Canada Machine Learning Group Technische Universität Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany

The feature vector mapping used to represent chemical systems is a key factor governing the superior data-efficiency of kernel based quantum machine learning (QML) models applicable throughout chemical compound space. Unfortunately, the most accurate representations require a high dimensional feature mapping, thereby imposing a considerable computational burden on model training and use. We introduce compact yet accurate, linear scaling QML representations based on atomic Gaussian many-body distribution functionals (MBDF), and their derivatives. Weighted density functions (DF) of MBDF values are used as global representations which are constant in size, i.e. invariant with respect to the number of atoms. We report predictive performance and training data efficiency that is competitive with state of the art for two diverse datasets of organic molecules, QM9 and QMugs. Generalization capability has been investigated for atomization energies, HOMO-LUMO eigenvalues and gap, internal energies at 0 K, zero point vibrational energies, dipole moment norm, static isotropic polarizability, and heat capacity as encoded in QM9. MBDF based QM9 performance lowers the optimal Pareto front spanned between sampling and training cost to compute node minutes, effectively sampling chemical compound space with chemical accuracy at a sampling rate of ∼ 48 molecules per core second. © 2023, CC0.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

XAI for Transformers: Better Explanations through Conservative Propagation

arXiv

引用

arXiv 2022年

作者： Ali, Ameen Ali Schnake, Thomas Eberle, Oliver Montavon, Grégoire Müller, Klaus-Robert Wolf, Lior The School of Computer Science Tel-Aviv University Israel Machine Learning Group Technische Universität Berlin Berlin Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin Germany Department of Artificial Intelligence Korea University Seoul Korea Republic of Max Planck Institute for Informatics Saarbrücken Germany

Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on gradient information, have been proposed. We show that the gradient in a Transformer reflects the function only locally, and thus fails to reliably identify the contribution of input features to the prediction. We identify Attention Heads and LayerNorm as the main reasons for such unreliable explanations and propose a more stable way for propagation through these layers. Our proposal, which can be seen as a proper extension of the well-established LRP method to Transformers, is shown both theoretically and empirically to overcome the deficiency of a simple gradient-based approach, and achieves state-of-the-art explanation performance on a broad range of Transformer models and datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

OADAT: Experimental and Synthetic Clinical Optoacoustic data for Standardized Image Processing

arXiv

引用

arXiv 2022年

作者： Ozdemir, Firat Lafci, Berkan Deán-Ben, Xosé Luís Razansky, Daniel Perez-Cruz, Fernando Swiss Data Science Center ETH Zurich and EPFL Zurich Switzerland Institute of Pharmacology and Toxicology Institute for Biomedical Engineering Faculty of Medicine University of Zurich Switzerland Institute for Biomedical Engineering Department of Information Technology and Electrical Engineering ETH Zurich Switzerland Institute for Machine Learning Department of Computer Science ETH Zurich Switzerland

Optoacoustic (OA) imaging is based on excitation of biological tissues with nanosecond-duration laser pulses followed by subsequent detection of ultrasound waves generated via light-absorption-mediated thermoelastic expansion. OA imaging features a powerful combination between rich optical contrast and high resolution in deep tissues. This enabled the exploration of a number of attractive new applications both in clinical and laboratory settings. However, no standardized datasets generated with different types of experimental set-up and associated processing methods are available to facilitate advances in broader applications of OA in clinical settings. This complicates an objective comparison between new and established data processing methods, often leading to qualitative results and arbitrary interpretations of the data. In this paper, we provide both experimental and synthetic OA raw signals and reconstructed image domain datasets rendered with different experimental parameters and tomographic acquisition geometries. We further provide trained neural networks to tackle three important challenges related to OA image processing, namely accurate reconstruction under limited view tomographic conditions, removal of spatial undersampling artifacts and anatomical segmentation for improved image reconstruction. Specifically, we define 44 experiments corresponding to the aforementioned challenges as benchmarks to be used as a reference for the development of more advanced processing methods. © 2022, CC BY-NC-SA.

关键词： Photoacoustic effect

来源：评论

学校读者我要写书评

暂无评论

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement learning

arXiv

引用

arXiv 2022年

作者： Steinparz, Christian Schmied, Thomas Paischer, Fabian Dinu, Marius-Constantin Patil, Vihang Bitto-Nemling, Angela Eghbal-Zadeh, Hamid Hochreiter, Sepp ELLIS Unit Linz and LIT AI Lab Institute for Machine Learning Johannes Kepler University Linz Austria Visual Data Science Lab Institute of Compute Graphics Johannes Kepler University Linz Austria Dynatrace Research Linz Austria Vienna Austria

In lifelong learning, an agent learns throughout its entire life without resets, in a constantly changing environment, as we humans do. Consequently, lifelong learning comes with a plethora of research problems such as continual domain shifts, which result in non-stationary rewards and environment dynamics. These non-stationarities are difficult to detect and cope with due to their continuous nature. Therefore, exploration strategies and learning methods are required that are capable of tracking the steady domain shifts, and adapting to them. We propose Reactive Exploration to track and react to continual domain shifts in lifelong reinforcement learning, and to update the policy correspondingly. To this end, we conduct experiments in order to investigate different exploration strategies. We empirically show that representatives of the policy-gradient family are better suited for lifelong learning, as they adapt more quickly to distribution shifts than Q-learning. Thereby, policy-gradient methods profit the most from Reactive Exploration and show good results in lifelong learning with continual domain shifts. Our code is available at: https://***/ml-jku/reactive-exploration. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Heat flux for semilocal machine-learning potentials

引用

Physical Review B 2023年第10期108卷 L100302-L100302页

作者： Marcel F. Langer Florian Knoop Christian Carbogno Matthias Scheffler Matthias Rupp Machine Learning Group Technische Universität Berlin 10587 Berlin Germany Berlin Institute for the Foundations of Learning and Data 10623 Berlin Germany The NOMAD Laboratory at the FHI of the Max-Planck-Gesellschaft and IRIS Adlershof of the Humboldt Universität zu Berlin 14195 Berlin Germany Theoretical Physics Division Department of Physics Chemistry and Biology (IFM) Linköping University 581 83 Linköping Sweden Department of Computer and Information Science University of Konstanz 78464 Konstanz Germany Materials Research and Technology Department Luxembourg Institute of Science and Technology Belvaux Luxembourg

The Green-Kubo (GK) method is a rigorous framework for heat transport simulations in materials. However, it requires an accurate description of the potential-energy surface and carefully converged statistics. machine-learning potentials can achieve the accuracy of first-principles simulations while allowing to reach well beyond their simulation time and length scales at a fraction of the cost. In this Letter, we explain how to apply the GK approach to the recent class of message-passing machine-learning potentials, which iteratively consider semilocal interactions beyond the initial interaction cutoff. We derive an adapted heat flux formulation that can be implemented using automatic differentiation without compromising computational efficiency. The approach is demonstrated and validated by calculating the thermal conductivity of zirconium dioxide across temperatures.

关键词： Lattice thermal conductivity machine learning Molecular dynamics Neural network simulations

来源：评论

学校读者我要写书评

暂无评论

learning Trivializing Gradient Flows for Lattice Gauge Theories

arXiv

引用

arXiv 2022年

作者： Bacchio, Simone Kessel, Pan Schaefer, Stefan Vaitl, Lorenz Computation-based Science and Technology Research Center The Cyprus Institute Nicosia Cyprus Machine Learning Group Technische Universität Berlin Berlin Germany BIFOLD—Berlin Institute for the Foundations of Learning and Data Berlin Germany John Von Neumann-Institut für Computing NIC Deutsches Elektronen-Synchrotron DESY Germany

We propose a unifying approach that starts from the perturbative construction of trivializing maps by Lüscher and then improves on it by learning. The resulting continuous normalizing flow model can be implemented using common tools of lattice field theory and requires several orders of magnitude fewer parameters than any existing machine learning approach. Specifically, our model can achieve competitive performance with as few as 14 parameters while existing deep-learning models have around 1 million parameters for SU(3) Yang–Mills theory on a 162 lattice. This has obvious consequences for training speed and interpretability. It also provides a plausible path for scaling machine-learning approaches toward realistic theories. © 2022, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DFingerNet: Noise-Adaptive Speech Enhancement for Hearing Aids

arXiv

引用

arXiv 2025年

作者： Tsangko, Iosif Triantafyllopoulos, Andreas Müller, Michael Schröter, Hendrik Schuller, Björn W. EIHW – Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg Germany CHI – Chair of Health Informatics Technical University of Munich Germany MCML – Munich Center for Machine Learning Munich Germany WS Audiology Research and Development Erlangen Germany GLAM – Group on Language Audio & Music Imperial College London United Kingdom MDSI – Munich Data Science Institute Munich Germany

The DeepFilterNet (DFN) architecture was recently proposed as a deep learning model suited for hearing aid devices. Despite its competitive performance on numerous benchmarks, it still follows a ‘one-size-fits-all’ approach, which aims to train a single, monolithic architecture that generalises across different noises and environments. However, its limited size and computation budget can hamper its generalisability. Recent work has shown that in-context adaptation can improve performance by conditioning the denoising process on additional information extracted from background recordings to mitigate this. These recordings can be offloaded outside the hearing aid, thus improving performance while adding minimal computational overhead. We introduce these principles to the DFN model, thus proposing the DFingerNet (DFiN) model, which shows superior performance on various benchmarks inspired by the DNS Challenge. Copyright © 2025, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

GatedxLSTM: A Multimodal Affective Computing Approach for Emotion Recognition in Conversations

arXiv

引用

arXiv 2025年

作者： Li, Yupei Sun, Qiyang Murthy, Sunil Munthumoduku Krishna Alturki, Emran Schuller, Björn W. GLAM Department of Computing Imperial College London United Kingdom CHI – Chair of Health Informatics MRI Technical University of Munich Germany CHI – Chair of Health Informatics Technical University of Munich Germany relAI – The Konrad Zuse School of Excellence in Reliable AI Munich Germany MDSI – Munich Data Science Institute Munich Germany MCML – Munich Center for Machine Learning Munich Germany

Affective Computing (AC) is essential for advancing Artificial General Intelligence (AGI), with emotion recognition serving as a key component. However, human emotions are inherently dynamic, influenced not only by an individual’s expressions but also by interactions with others, and single-modality approaches often fail to capture their full dynamics. Multimodal Emotion Recognition (MER) leverages multiple signals but traditionally relies on utterance-level analysis, overlooking the dynamic nature of emotions in conversations. Emotion Recognition in Conversation (ERC) addresses this limitation, yet existing methods struggle to align multimodal features and explain why emotions evolve within dialogues. To bridge this gap, we propose GatedxLSTM, a novel speech-text multimodal ERC model that explicitly considers voice and transcripts of both the speaker and their conversational partner(s) to identify the most influential sentences driving emotional shifts. By integrating Contrastive Language-Audio Pretraining (CLAP) for improved cross-modal alignment and employing a gating mechanism to emphasise emotionally impactful utterances, GatedxLSTM enhances both interpretability and performance. Additionally, the Dialogical Emotion Decoder (DED) refines emotion predictions by modelling contextual dependencies. Experiments on the IEMOCAP dataset demonstrate that GatedxLSTM achieves state-of-the-art (SOTA) performance among open-source methods in four-class emotion classification. These results validate its effectiveness for ERC applications and provide an interpretability analysis from a psychological perspective. © 2025, CC BY.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Is L2 physics-informed loss always suitable for training physics-informed neural network? 22

Is L2 physics-informed loss always suitable for training phy...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Chuwei Wang Shanda Li Di He Liwei Wang School of Mathematical Sciences Peking University Machine Learning Department School of Computer Science Carnegie Mellon University and Zhejiang Lab National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University and Center for Data Science Peking University

ISBN: (纸本)9781713871088

The Physics-Informed Neural Network (PINN) approach is a new and promising way to solve partial differential equations using deep learning. The L2 Physics- Informed Loss is the de-facto standard in training Physics-Informed Neural Networks. In this paper, we challenge this common practice by investigating the relationship between the loss function and the approximation quality of the learned solution. In particular, we leverage the concept of stability in the literature of partial differential equation to study the asymptotic behavior of the learned solution as the loss approaches zero. With this concept, we study an important class of high-dimensional non-linear PDEs in optimal control, the Hamilton-Jacobi- Bellman (HJB) Equation, and prove that for general Lp Physics-Informed Loss, a wide class of HJB equation is stable only if p is sufficiently large. Therefore, the commonly used L2 loss is not suitable for training PINN on those equations, while L∞ loss is a better choice. Based on the theoretical insight, we develop a novel PINN training algorithm to minimize the L∞ loss for HJB equations which is in a similar spirit to adversarial training. The effectiveness of the proposed algorithm is empirically demonstrated through experiments.

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：