arXiv 2108.025712021-08cs.LGmath.OC

Learning Linearized Assignment Flows for Image Labeling

Heidelberg University（海德堡大学）

Alexander Zeilmann, Stefania Petra, Christoph Schnörr

英文摘要：

We introduce a novel algorithm for estimating optimal parameters of linearized assignment flows for image labeling. An exact formula is derived for the parameter gradient of any loss function that is constrained by the linear system of ODEs determining the linearized assignment flow. We show how to efficiently evaluate this formula using a Krylov subspace and a low-rank approximation. This enables us to perform parameter learning by Riemannian gradient descent in the parameter space, without the need to backpropagate errors or to solve an adjoint equation. Experiments demonstrate that our method performs as good as highly-tuned machine learning software using automatic differentiation. Unlike methods employing automatic differentiation, our approach yields a low-dimensional representation of internal parameters and their dynamics which helps to understand how assignment flows and more generally neural networks work and perform.

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

Self-Certifying Classification by Linearized Deep Assignment

Heidelberg University（海德堡大学）

We propose a novel class of deep stochastic predictors for classifying metric data on graphs within the PAC-Bayes risk certification paradigm. Classifiers are realized as linearly parametrized deep assignment flows with random initial conditions. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables (i) to use risk bounds as training objectives for learning posterior distributions on the hypothesis space and (ii) to compute tight out-of-sample risk certificates of randomized classifiers more efficiently than related work. Comparison with empirical test se…

2022-02-18cs.LGmath.OCstat.ML

Self-Assignment Flows for Unsupervised Data Labeling on Graphs

Heidelberg University（海德堡大学）

This paper extends the recently introduced assignment flow approach for supervised image labeling to unsupervised scenarios where no labels are given. The resulting self-assignment flow takes a pairwise data affinity matrix as input data and maximizes the correlation with a low-rank matrix that is parametrized by the variables of the assignment flow, which entails an assignment of the data to themselves through the formation of latent labels (feature prototypes). A single user parameter, the neighborhood size for the geometric regularization of assignments, drives the entire process. By smooth…

2020-03-24cs.CVcs.LG

半监督多标签学习中类分布感知的伪标签标注

Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning

RIKEN Center for AIP（理化学研究所人工智能研究中心）；University of Tokyo（东京大学）

本文针对半监督多标签学习（SSMLL）中伪标签易出现假阳性或漏标问题，提出类感知伪标签标注方法（CAP），通过引入类感知阈值与类分布感知策略对齐伪标签与真实分布，并在理论上验证了估计分布正确性及泛化误差界，多基准实验证实其有效性。

2023-05-20cs.LG

Unsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment

Heidelberg University（海德堡大学）

This paper introduces the unsupervised assignment flow that couples the assignment flow for supervised image labeling with Riemannian gradient flows for label evolution on feature manifolds. The latter component of the approach encompasses extensions of state-of-the-art clustering approaches to manifold-valued data. Coupling label evolution with the spatially regularized assignment flow induces a sparsifying effect that enables to learn compact label dictionaries in an unsupervised manner. Our approach alleviates the requirement for supervised labeling to have proper labels at hand, because an…

2019-12-16cs.CVcs.LGmath.OC

Large-Scale Multi-Label Learning with Incomplete Label Assignments

University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Tsinghua University（清华大学）；Yahoo! Research（雅虎研究院）；Microsoft（微软）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）

Multi-label learning deals with the classification problems where each instance can be assigned with multiple labels simultaneously. Conventional multi-label learning approaches mainly focus on exploiting label correlations. It is usually assumed, explicitly or implicitly, that the label sets for training instances are fully labeled without any missing labels. However, in many real-world multi-label datasets, the label assignments for training instances can be incomplete. Some ground-truth labels can be missed by the labeler from the label set. This problem is especially typical when the numbe…

2014-07-06cs.LG

用于伪标签的置信 Sinkhorn 分配

Confident Sinkhorn Allocation for Pseudo-Labeling

Amazon（亚马逊）

本文针对无结构数据下伪标签易因过度自信和阈值敏感而错误分配的问题，提出基于最优传输、仅向高置信样本分配标签的 CSA，并改进集成模型 PAC-Bayes 界，性能超过现有方法。

2024-03-05cs.LG

更多相关论文收起更多论文

基于图形模型的图像标注：利用Wasserstein消息与几何分配

Image Labeling Based on Graphical Models Using Wasserstein Messages and Geometric Assignment

Image and Pattern Analysis Group, Heidelberg University, Germany（海德堡大学图像与模式分析组）；Heidelberg Collaboratory for Image Processing, Heidelberg University, Germany（海德堡图像处理协同实验室）

本文提出基于离散图模型的最大后验推断新方法，利用局部Wasserstein距离近似目标函数并实现并行收敛。

2018-01-09cs.CVcs.LGcs.NA

跨组分配的一致标注：条件平均处理效应估计中的方差缩减

Consistent Labeling Across Group Assignments: Variance Reduction in Conditional Average Treatment Effect Estimation

National Taiwan University（台湾大学）

本文针对CATE估计中同一实例在不同组分配下学习行为不一致的问题，提出通用方法CLAGA，通过消除不一致性显著提升现有算法的估计性能。

2025-07-06cs.LGstat.MEstat.ML

KGOT: 统一知识图谱和最优传输伪标签法用于分子-蛋白质相互作用预测

KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction

Department of Computer Science and Engineering, University at Buffalo（大学计算机科学与工程系）；Mohamed bin Zayed University of Artificial Intelligence（莫莫德·本·扎耶德人工智能大学）；Weizmann Institute of Science（魏兹曼科学研究所）

KGOT通过整合知识图谱与最优传输伪标签法，提升分子-蛋白质相互作用预测的准确性和零样本能力，拓展生物数据应用的范式。

2025-12-10cs.LG

Task Selection for Bandit-Based Task Assignment in Heterogeneous Crowdsourcing

Tokyo Institute of Technology（东京工业大学）；The University of Tokyo（东京大学）

Task selection (picking an appropriate labeling task) and worker selection (assigning the labeling task to a suitable worker) are two major challenges in task assignment for crowdsourcing. Recently, worker selection has been successfully addressed by the bandit-based task assignment (BBTA) method, while task selection has not been thoroughly investigated yet. In this paper, we experimentally compare several task selection strategies borrowed from active learning literature, and show that the least confidence strategy significantly improves the performance of task assignment in crowdsourcing.

2015-07-26cs.LG

Bounded Expectation of Label Assignment: Dataset Annotation by Supervised Splitting with Bias-Reduction Techniques

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

Annotating large unlabeled datasets can be a major bottleneck for machine learning applications. We introduce a scheme for inferring labels of unlabeled data at a fraction of the cost of labeling the entire dataset. Our scheme, bounded expectation of label assignment (BELA), greedily queries an oracle (or human labeler) and partitions a dataset to find data subsets that have mostly the same label. BELA can then infer labels by majority vote of the known labels in each subset. BELA determines whether to split or label from a subset by maximizing a lower bound on the expected number of correctly…

2021-02-25cs.LGstat.ML

最优标签分配与采样用于存在不完美标签的主动学习

Active Learning with Imperfect Labels: Optimal Labeler Assignment and Sample Selection

School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332, USA（工业与系统工程学院佐治亚理工学院阿拉巴马州亚特兰大 30332, 美国）；Ford Motor Company（福特汽车公司）

本文提出了一种新的主动学习框架，通过优化标签分配和采样方法，减少噪声影响以提高分类性能。

2026-10-01cs.AIcs.LGmath.OC

Assigning Species Information to Corresponding Genes by a Sequence Labeling Framework

National Center for Biotechnology Information (NCBI)（美国国家生物技术信息中心（NCBI））；National Library of Medicine (NLM)（美国国家医学图书馆（NLM））；National Institutes of Health (NIH)（美国国立卫生研究院（NIH））

The automatic assignment of species information to the corresponding genes in a research article is a critically important step in the gene normalization task, whereby a gene mention is normalized and linked to a database record or identifier by a text-mining algorithm. Existing methods typically rely on heuristic rules based on gene and species co-occurrence in the article, but their accuracy is suboptimal. We therefore developed a high-performance method, using a novel deep learning-based framework, to classify whether there is a relation between a gene and a species. Instead of the traditio…

2022-05-08cs.CLcs.IRcs.LG

Deep Variational Clustering Framework for Self-labeling of Large-scale Medical Images

Technical University of Munich（慕尼黑工业大学）；Massachusetts Eye and Ear Hospital（马萨诸塞眼耳医院）；Harvard Medical School（哈佛医学院）；LMU Munich（慕尼黑大学）

We propose a Deep Variational Clustering (DVC) framework for unsupervised representation learning and clustering of large-scale medical images. DVC simultaneously learns the multivariate Gaussian posterior through the probabilistic convolutional encoder and the likelihood distribution with the probabilistic convolutional decoder; and optimizes cluster labels assignment. Here, the learned multivariate Gaussian posterior captures the latent distribution of a large set of unlabeled images. Then, we perform unsupervised clustering on top of the variational latent space using a clustering loss. In …

2021-09-22cs.CVcs.LGeess.IV

用于表示和学习离散数据联合分布的生成赋值流

Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data

Heidelberg University（海德堡大学）；University of Augsburg（奥格斯堡大学）

本研究提出一种基于随机赋值流的新型生成模型，通过条件黎曼流匹配无仿真训练，可高效表示和采样离散随机变量的联合分布，在多类别场景下扩展性优于现有方法。

2025-01-13cs.LGstat.ML

Sigma 流用于图像与数据标注及结构化预测学习

Sigma Flows for Image and Data Labeling and Learning Structured Prediction

Heidelberg University（海德堡大学）；University of Augsburg（奥格斯堡大学）

本文提出 sigma 流模型，结合 Laplace-Beltrami 与分配流方法，通过黎曼梯度流和几何 PDE 实现结构化预测，并指出其与 transformer 的相似性，实验验证了其表现力。

2025-09-11cs.CVcs.LGmath.DS