首页/论文/2005.01463

arXiv 2005.014632020-05cs.LGeess.IVphysics.flu-dynstat.ML

MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Framework

University of California, Berkeley（加州大学伯克利分校）；Stanford University（斯坦福大学）；California Institute of Technology（加州理工学院）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；NVIDIA（英伟达）

Chiyu Max Jiang, Soheil Esmaeilzadeh, Kamyar Azizzadenesheli, Karthik Kashinath, Mustafa Mustafa, Hamdi A. Tchelepi, Philip Marcus, Prabhat, Anima Anandkumar

备注：: Supplementary Video: https://youtu.be/mjqwPch9gDo. Accepted to SC20

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

We propose MeshfreeFlowNet, a novel deep learning-based super-resolution framework to generate continuous (grid-free) spatio-temporal solutions from the low-resolution inputs. While being computationally efficient, MeshfreeFlowNet accurately recovers the fine-scale quantities of interest. MeshfreeFlowNet allows for: (i) the output to be sampled at all spatio-temporal resolutions, (ii) a set of Partial Differential Equation (PDE) constraints to be imposed, and (iii) training on fixed-size inputs on arbitrarily sized spatio-temporal domains owing to its fully convolutional encoder. We empirically study the performance of MeshfreeFlowNet on the task of super-resolution of turbulent flows in the Rayleigh-Benard convection problem. Across a diverse set of evaluation metrics, we show that MeshfreeFlowNet significantly outperforms existing baselines. Furthermore, we provide a large scale implementation of MeshfreeFlowNet and show that it efficiently scales across large clusters, achieving 96.80% scaling efficiency on up to 128 GPUs and a training time of less than 4 minutes.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Constrained Labeling for Weakly Supervised Learning

Virginia Tech（弗吉尼亚理工大学）；Tufts University（塔夫茨大学）

Curation of large fully supervised datasets has become one of the major roadblocks for machine learning. Weak supervision provides an alternative to supervised learning by training with cheap, noisy, and possibly correlated labeling functions from varying sources. The key challenge in weakly supervised learning is combining the different weak supervision signals while navigating misleading correlations in their errors. In this paper, we propose a simple data-free approach for combining weak supervision signals by defining a constrained space for the possible labels of the weak signals and trai…

2021-05-29cs.AIcs.LGstat.ML

偏微分方程中稀疏观测的超分辨率：一种物理约束卷积神经网络方法

Super-resolving sparse observations in partial differential equations: A physics-constrained convolutional neural network approach

Imperial College London（帝国理工学院）；Alan Turing Institute（艾伦·图灵研究所）

提出物理约束卷积神经网络（PC-CNN），利用先验物理知识从稀疏观测中推断高分辨率解，无需高分辨率训练数据，适用于混沌湍流等复杂系统，为实验数据超分辨率提供新途径。

2023-06-19cs.LGphysics.flu-dyn

Physics-constrained indirect supervised learning

Peng Cheng Laboratory（鹏城实验室）；Southern University of Science and Technology（南方科技大学）

This study proposes a supervised learning method that does not rely on labels. We use variables associated with the label as indirect labels, and construct an indirect physics-constrained loss based on the physical mechanism to train the model. In the training process, the model prediction is mapped to the space of value that conforms to the physical mechanism through the projection matrix, and then the model is trained based on the indirect labels. The final prediction result of the model conforms to the physical mechanism between indirect label and label, and also meets the constraints of th…

2020-04-26cs.LGeess.SP

Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models

School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；Dept. of Computer Science, Brown University（布朗大学计算机科学系）；School of Information and Computer Sciences, Univ. of California, Irvine（加州大学欧文分校信息与计算机科学学院）；Massachusetts General Hospital（麻省总医院）

Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly balances two goals: recovery of faithful generative explanations of high-dimensional data, and accurate prediction of associated semantic labels. Existing approaches fail to achieve these goals due to an incomplete treatment of a fundamental asymmetry: the intended application is always predicting labels from data, not data from labels. Our prediction-constra…

2017-07-23cs.AIcs.LGstat.ML

OracleZoom：基于在策略自蒸馏的参考约束递归图像超分辨率

OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution

University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）

OracleZoom提出一种受在策略蒸馏启发的参考约束递归超分辨率框架，通过携带真实标签证据并采用无参考质量目标，在七个数据集上实现最先进的超分辨率质量，平均CLIPIQA达0.713，并显著减少幻觉。

2026-09-09cs.AIcs.CLcs.CV

Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior

Soochow University（苏州大学）；Hefei University of Technology（合肥工业大学）；Harbin Institute of Technology（哈尔滨工业大学）；Pengcheng Laboratory（鹏城实验室）；Sea AI Labs

Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces. In this paper, we technically propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net, for learning the hierarchical coupled representations. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Specifically, DS2CF-Net designs a deep coupl…

2021-09-07cs.LGstat.ML

更多相关论文收起更多论文

Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet

Eindhoven University of Technology（埃因霍温理工大学）；Shandong University of Science and Technology（山东科技大学）；Philips Research（飞利浦研究院）

Catheter segmentation in 3D ultrasound is important for computer-assisted cardiac intervention. However, a large amount of labeled images are required to train a successful deep convolutional neural network (CNN) to segment the catheter, which is expensive and time-consuming. In this paper, we propose a novel catheter segmentation approach, which requests fewer annotations than the supervised learning method, but nevertheless achieves better performance. Our scheme considers a deep Q learning as the pre-localization step, which avoids voxel-level annotation and which can efficiently localize t…

2020-06-25cs.CVcs.LGeess.IV

Self-Supervised Primal-Dual Learning for Constrained Optimization

Georgia Institute of Technology（佐治亚理工学院）

This paper studies how to train machine-learning models that directly approximate the optimal solutions of constrained optimization problems. This is an empirical risk minimization under constraints, which is challenging as training must balance optimality and feasibility conditions. Supervised learning methods often approach this challenge by training the model on a large collection of pre-solved instances. This paper takes a different route and proposes the idea of Primal-Dual Learning (PDL), a self-supervised training method that does not require a set of pre-solved instances or an optimiza…

2022-11-22cs.LGmath.OC

用于近似约束优化的自监督等式嵌入深度拉格朗日对偶

Self-supervised Equality Embedded Deep Lagrange Dual for Approximate Constrained Optimization

本文提出无标签框架DeepLDE，通过将等式约束嵌入神经网络并用原始-对偶方法施加不等式约束，实现快速且确保可行性的近似约束优化，计算速度比传统求解器快5至250倍。

2024-09-23cs.LGmath.OC

约束优化的迭代求解器的自监督学习

Self-Supervised Learning of Iterative Solvers for Constrained Optimization

Chair of Process Automation Systems, TU Dortmund University（过程自动化系统教授会，杜伊斯堡-艾森大学）

提出一种基于学习的迭代求解器，通过神经网络预测初始解并用学习型迭代器精炼，利用KKT条件设计损失函数实现自监督训练，在非凸问题上比IPOPT快一个数量级且精度更高。

2026-06-16cs.LGmath.OC