首页/论文/2004.05713

arXiv 2004.057132020-04-27cs.CV

Learning Spatial Relationships between Samples of Patent Image Shapes

Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

Juan Castorena, Manish Bhattarai, Diane Oyen

英文摘要：

Binary image based classification and retrieval of documents of an intellectual nature is a very challenging problem. Variations in the binary image generation mechanisms which are subject to the document artisan designer including drawing style, view-point, inclusion of multiple image components are plausible causes for increasing the complexity of the problem. In this work, we propose a method suitable to binary images which bridges some of the successes of deep learning (DL) to alleviate the problems introduced by the aforementioned variations. The method consists on extracting the shape of interest from the binary image and applying a non-Euclidean geometric neural-net architecture to learn the local and global spatial relationships of the shape. Empirical results show that our method is in some sense invariant to the image generation mechanism variations and achieves results outperforming existing methods in a patent image dataset benchmark.

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

用于专利图像检索的层次化多正样本对比学习

Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval

Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；TKH AI（TKH人工智能）

针对专利图像检索忽视层次关系的问题，提出利用洛迦诺国际分类的层次化多正样本对比损失，在DeepPatent2上提升检索效果，且对低参数模型有效。

2025-06-19cs.CVcs.IRcs.LG

Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules

School of Software, Tsinghua University（清华大学软件学院）；Department of Computer Science, University of Maryland at College Park（马里兰大学帕克分校计算机科学系）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）

Learning discriminative shape representation directly on point clouds is still challenging in 3D shape analysis and understanding. Recent studies usually involve three steps: first splitting a point cloud into some local regions, then extracting corresponding feature of each local region, and finally aggregating all individual local region features into a global feature as shape representation using simple max pooling. However, such pooling-based feature aggregation methods do not adequately take the spatial relationships between local regions into account, which greatly limits the ability to …

2019-08-29cs.CV

CLIP纹理-形状偏倚的动态演变及其与人类对齐和模型鲁棒性的关系

On the dynamic evolution of CLIP texture-shape bias and its relationship to human alignment and model robustness

Image Processing Lab, Universitat de Valencia, Spain（瓦伦西亚大学图像处理实验室）；Centro de Biomateriales e Ingenieria Tisular, Universitat Politecnica de Valencia, Spain（瓦伦西亚理工大学生物材料与组织工程中心）；Computer Vision Center, Spain（西班牙计算机视觉中心）；Universitat Autònoma de Barcelona, Spain（巴塞罗那自治大学）

本文研究CLIP模型在训练过程中纹理-形状偏倚的演变，揭示其与人类感知对齐及模型鲁棒性的关系。

2025-12-19cs.CV

Texture Characterization by Using Shape Co-occurrence Patterns

State Key Lab. LIESMARS, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；CNRS LTCI, Telecom ParisTech（法国国家科学研究中心LTCI实验室，巴黎高等电信学院）；Electronic Information School, Huazhong University of Science and Technology（华中科技大学电子信息学院）

Texture characterization is a key problem in image understanding and pattern recognition. In this paper, we present a flexible shape-based texture representation using shape co-occurrence patterns. More precisely, texture images are first represented by tree of shapes, each of which is associated with several geometrical and radiometric attributes. Then four typical kinds of shape co-occurrence patterns based on the hierarchical relationship of the shapes in the tree are learned as codewords. Three different coding methods are investigated to learn the codewords, with which, any given texture …

2017-02-10cs.CV

澄清关于形状偏置、准确性与鲁棒性之间关系的神话

Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness

Gina Cody School of Engineering, Concordia University（康考迪亚大学吉娜·科迪工程学院）；Zetane Systems Inc.（泽坦系统公司）

本文通过评估39种数据增强方法，证明形状偏置增加并不必然提升OOD鲁棒性，并发现适当的数据增强可同时提高域内准确率与OOD鲁棒性。

2024-06-07cs.CV

基于共现的字体印象词标签嵌入

Embedding Font Impression Word Tags Based on Co-occurrence

Kyushu University（九州大学）

本文提出一种基于共现关系的谱嵌入方法，为字体印象标签生成相似向量，优于BERT和CLIP，在印象引导的字体生成中表现更好。

2025-08-26cs.CV

更多相关论文收起更多论文

Primitive Graph Learning for Unified Vector Mapping

Huawei Technologies（华为技术有限公司）；Wuhan University（武汉大学）

Large-scale vector mapping is important for transportation, city planning, and survey and census. We propose GraphMapper, a unified framework for end-to-end vector map extraction from satellite images. Our key idea is a novel unified representation of shapes of different topologies named "primitive graph", which is a set of shape primitives and their pairwise relationship matrix. Then, we convert vector shape prediction, regularization, and topology reconstruction into a unique primitive graph learning problem. Specifically, GraphMapper is a generic primitive graph learning network based on gl…

2022-11-11cs.CV

CNN双重下降与学习过程中形状/纹理偏差之间的关系

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process

Tokyo Denki University（东京电机大学）；Tokyo Institute of Technology（东京工业大学）；Tenchijin Inc.（天进公司）；National Institute of Advanced Industrial Science and Technology（国立先进工业技术研究所）

本文研究了CNN学习过程中形状/纹理偏差与逐轮次双重下降现象的关联，发现两者同步出现，且该现象在无标签噪声条件下也可能发生，有助于揭示双重下降机制。

2025-03-04cs.CVcs.LG

Anatomically Parameterized Statistical Shape Model: Explaining Morphometry through Statistical Learning

IMT Atlantique（大西洋国立高等矿业电信学院）；LaTIM UMR 1101, Inserm（法国国家健康与医学研究院LaTIM UMR 1101实验室）；CHRU de Brest（布雷斯特大学区域医院中心）；SCMIA, SIU（SIU SCMIA）

Statistical shape models (SSMs) are a popular tool to conduct morphological analysis of anatomical structures which is a crucial step in clinical practices. However, shape representations through SSMs are based on shape coefficients and lack an explicit one-to-one relationship with anatomical measures of clinical relevance. While a shape coefficient embeds a combination of anatomical measures, a formalized approach to find the relationship between them remains elusive in the literature. This limits the use of SSMs to subjective evaluations in clinical practices. We propose a novel SSM controll…

2022-02-17cs.CVeess.IV

Hypothesize and Bound: A Computational Focus of Attention Mechanism for Simultaneous 3D Shape Reconstruction, Pose Estimation and Classification from a Single 2D Image

Johns Hopkins University（约翰斯·霍普金斯大学）

This article presents a mathematical framework to simultaneously tackle the problems of 3D reconstruction, pose estimation and object classification, from a single 2D image. In sharp contrast with state of the art methods that rely primarily on 2D information and solve each of these three problems separately or iteratively, we propose a mathematical framework that incorporates prior "knowledge" about the 3D shapes of different object classes and solves these problems jointly and simultaneously, using a hypothesize-and-bound (H&B) algorithm. In the proposed H&B algorithm one hypothesis is defin…

2011-09-26cs.CGcs.CV

Learning Body-Aware 3D Shape Generative Models

Brown University（布朗大学）；Simon Fraser University（西蒙弗雷泽大学）

The shape of many objects in the built environment is dictated by their relationships to the human body: how will a person interact with this object? Existing data-driven generative models of 3D shapes produce plausible objects but do not reason about the relationship of those objects to the human body. In this paper, we learn body-aware generative models of 3D shapes. Specifically, we train generative models of chairs, an ubiquitous shape category, which can be conditioned on a given body shape or sitting pose. The body-shape-conditioned models produce chairs which will be comfortable for a p…

2022-01-20cs.CVcs.GRcs.LG

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）

Convolutional Neural Networks (CNNs) are known to rely more on local texture rather than global shape when making decisions. Recent work also indicates a close relationship between CNN's texture-bias and its robustness against distribution shift, adversarial perturbation, random corruption, etc. In this work, we attempt at improving various kinds of robustness universally by alleviating CNN's texture bias. With inspiration from the human visual system, we propose a light-weight model-agnostic method, namely Informative Dropout (InfoDrop), to improve interpretability and reduce texture bias. Sp…

2020-08-10cs.CVcs.LGstat.ML