检索结果-内蒙古大学图书馆

ieee workshop on Applications of computer vision (WACV)

作者： Alexander H. Berger Laurin Lux Suprosanna Shit Ivan Ezhov Georgios Kaissis Martin J. Menten Daniel Rueckert Johannes C. Paetzold School of Computation Information and Technology Technical University of Munich Germany Munich Center for Machine Learning (MCML) Munich Germany Department of Quantitative Biomedicine University of Zurich Switzerland Institute for Machine Learning in Biomedical Imaging Helmholtz Munich Germany Department of Computing Imperial College London UK Weill Cornell Medicine Cornell University New York City USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Direct image-to-graph transformation is a challenging task that involves solving object detection and relationship prediction in a single model. Due to this task's complexity, large training datasets are rare in many domains, making the training of deep-learning methods challenging. This data sparsity necessitates transfer learning strategies akin to the state-of-the-art in general computer vision. In this work, we introduce a set of methods enabling cross-domain and cross-dimension learning for image-to-graph trans-formers. We propose (1) a regularized edge sampling loss to effectively learn object relations in multiple domains with different numbers of edges, (2) a domain adaptation frame-work for image-to-graph transformers aligning image- and graph-level features from different domains, and (3) a projection function that allows using 2D data for training 3D transformers. We demonstrate our method's utility in cross-domain and cross-dimension experiments, where we utilize labeled data from 2D road networks for simultaneous learning in vastly different target domains. Our method consistently outperforms standard transfer learning and self-supervised pretraining on challenging benchmarks, such as retinal or whole-brain vessel graph extraction. 1 1 Code: ***/AlexanderHBerger/cross-dim_i2g

关键词： Training computer vision Three-dimensional displays Image edge detection Roads Transfer learning Predictive models Transformers Retina Standards

来源：评论

学校读者我要写书评

暂无评论

RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples

RD-DPP: Rate-Distortion Theory Meets Determinantal Point Pro...

引用

ieee workshop on Applications of computer vision (WACV)

作者： Xiwen Chen Huayu Li Peijie Qiu Wenhui Zhu Rahul Amin Abolfazl Razi Clemson University University of Arizona Washington University in St. Louis Arizona State University MIT Lincoln Laboratory

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Selecting representative samples plays an indispensable role in many machine learning and computer vision applications under limited resources (e.g., limited communication bandwidth and computational power). Determinantal Point Process (DPP) is a widely used method for selecting the most diverse representative samples that can summarize a dataset. However, its adaptability to different tasks remains an open challenge, as it is challenging for DPP to perform task-specific tuning. In contrast, Rate-Distortion (RD) theory provides a way to measure task-specific diversity. However, optimizing RD for a data selection problem remains challenging because the quantity that needs to be optimized is the index set of the selected samples. To tackle these challenges, we first draw an inherent relationship between DPP and RD theory. Our theoretical derivation paves the way to take advantage of both RD and DPP for a task-specific data selection. To this end, we propose a novel method for task-specific data selection for multi-level classification tasks, named RD-DPP. Empirical studies on seven different datasets using five benchmark models demonstrate the effectiveness of the proposed RD-DPP method. Our method also outperforms recent strong competing methods, while exhibiting high generalizability to a variety of learning tasks. The source code is available on https://***/xiwencl/RD-DPP 1 .

关键词： Training computer vision Source coding Rate-distortion Data visualization Machine learning Bandwidth Benchmark testing Indexes Tuning

来源：评论

学校读者我要写书评

暂无评论

CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition

CLFace: A Scalable and Resource-Efficient Continual Learning...

引用

ieee workshop on Applications of computer vision (WACV)

作者： Md Mahedi Hasan Shoaib Meraj Sami Nasser Nasrabadi West Virginia University Morgantown West Virginia USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

An important aspect of deploying face recognition (FR) algorithms in real-world applications is their ability to learn new face identities from a continuous data stream. However, the online training of existing deep neural network-based FR algorithms, which are pre-trained offline on large-scale stationary datasets, encounter two major challenges: (I) catastrophic forgetting of previously learned identities, and (II) the need to store past data for complete retraining from scratch, leading to significant storage constraints and privacy concerns. In this paper, we introduce CLFace, a continual learning framework designed to preserve and incrementally extend the learned knowledge. CLFace eliminates the classification layer, resulting in a resource-efficient FR model that remains fixed throughout lifelong learning and provides label-free supervision to a student model, making it suitable for open-set face recog-nition during incremental steps. We introduce an objective function that employs feature-level distillation to reduce drift between feature maps of the student and teacher models across multiple stages. Additionally, it incorpo-rates a geometry-preserving distillation scheme to maintain the orientation of the teacher model's feature embedding. Furthermore, a contrastive knowledge distillation is incor-porated to continually enhance the discriminative power of the feature representation by matching similarities between new identities. Experiments on several benchmark FR datasets demonstrate that CLFace outperforms baseline approaches and state-of-the-art methods on unseen identities using both in-domain and out-of-domain datasets.

关键词： Training Continuing education Data privacy computer vision Face recognition Benchmark testing Linear programming

来源：评论

学校读者我要写书评

暂无评论

Forensic Iris Image-Based Post-Mortem Interval Estimation

Forensic Iris Image-Based Post-Mortem Interval Estimation

引用

ieee workshop on Applications of computer vision (WACV)

作者： Rasel Ahmed Bhuiyan Adam Czajka University of Notre Dame Notre Dame Indiana USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Post-mortem iris recognition is an emerging application of iris-based human identification in a forensic setup. One factor that may be useful in conditioning iris recognition methods is the tissue decomposition level, which is correlated with the post-mortem interval (PMI), i.e. the number of hours that have elapsed since death. PMI, however, is not always available, and its precise estimation remains one of the core challenges in forensic examination. This paper presents the first known to us method of the PMI estimation directly from iris images captured after death. To assess the feasibility of the iris-based PMI estimation, we designed models predicting the PMI from (a) near-infrared (NIR), (b) visible (RGB), and (c) multispectral (RGB+NIR) forensic iris images. Models were evaluated following a 10-fold cross-validation, in (S1) sample-disjoint, (S2) subject-disjoint, and (S3) cross-dataset scenarios. We explore two data balancing techniques for S3: resampling-based balancing (S3-real), and synthetic data-supplemented balancing (S3 -synthetic), We found that using the multispectral data offers a spectacularly low mean absolute error (MAE) of≈ 3.5 hours in the scenario (S1), a bit worse MAE ≈ 17.5 hours in the scenario (S2), and MAE ≈ 45.77 hours in the scenario (S3). Additionally, supplementing the training set with synthetically-generated forensic iris images (S3-synthetic) significantly enhances the models' ability to generalize to new NIR, RGB and multispectral data collected in a different lab. This suggests that if the environmental conditions are favorable (e.g., bodies are kept in low temperatures), forensic iris images provide features that are in-dicative of the PMI and can be automatically estimated.

关键词： Training computer vision Forensics Estimation Predictive models Data models Iris recognition Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Cross Image Feature Perturbation with Pseudo Label Fusion for Semi-Supervised Medical Image Segmentation

Cross Image Feature Perturbation with Pseudo Label Fusion fo...

引用

ieee workshop on Applications of computer vision (WACV)

作者： Minxia Xu Han Yang Bo Song Weida Hu Jinshui Miao Erkang Cheng Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou China University of Chinese Academy of Sciences Beijing China Institute of Intelligent Machines HFIPS Chinese Academy of Sciences Hefei China University of Science and Technology of China Hefei China

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Semi-supervised medical image segmentation aims to leverage a limited set of labeled images alongside a substantial volume of unlabeled images to train semantic segmentation models. Existing studies often employ consistency regularization to maximize the utilization of unlabeled data, thereby enhancing the model's robustness and accuracy. However, the methods for constructing perturbations at image-level on unlabeled data are typically simplistic, involving techniques such as color transformations, additive noise, which do not adequately leverage the precise and reliable supervisory information available from labeled images. To address this limitation, in addition to image perturbation, we propose a cross-image feature perturbation approach for semi-supervised medical image segmentation. This method utilizes feature information from labeled images to guide the refinement of ambiguous semantic representations in unlabeled images, thereby expanding the perturbation space more effectively. Moreover, recognizing the limitations of existing consistency regularization frameworks that rely on confidence thresholds to filter pseudo-labels, we introduce an uncertainty-based pseudo-label fusion strategy. This strategy mitigates the effects of unreliable predictions caused by perturbations by calculating the uncertainty and using it as a weight during pseudo-label fusion. We have conducted extensive experiments on the 2D ACDC and 3D LA datasets. The results demonstrate that our approach achieves performance comparable to the current state-of-the-art (SOTA) methods.

关键词： Solid modeling Three-dimensional displays Uncertainty Perturbation methods Semantic segmentation Semantics Information filters Robustness Streams Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A variational approach for the segmentation of the left ventricle in cardiac image analysis

引用

INTERNATIONAL JOURNAL OF computer vision 2002年第3期50卷 345-362页

作者： Paragios, N Siemens Corp Res Real Time Vis & Modeling Dept Princeton NJ 08540 USA

In this paper we propose a level set method to segment MR cardiac images. Our approach is based on a coupled propagation of two cardiac contours and integrates visual information with anatomical constraints. The visual information is expressed through a gradient vector flow-based boundary component and a region term that aims at best separating the cardiac contours/regions according to their global intensity properties. In order to deal with misleading visual support, an anatomical constraint is considered that couples the propagation of the cardiac contours according to their relative distance. The resulting motion equations are implemented using a level set approach and a fast and stable numerical approximation scheme, the Additive Operator Splitting. Encouraging experimental results are provided using real data.

关键词： left ventricle medical image segmentation gradient vector flow geodesic active regions level set methods

来源：评论

学校读者我要写书评

暂无评论

Stochastic motion and the level set method in computer vision:: Stochastic active contours

引用

INTERNATIONAL JOURNAL OF computer vision 2006年第1期69卷 7-25页

作者： Juan, Olivier Keriven, Renaud Postelnicu, Gheorghe ENPC CERTIS ENS Odyssee LabINRIA Sophia F-77455 Marne La Vallee France

Based on recent work on Stochastic Partial Differential Equations (SPDEs), this paper presents a simple and well-founded method to implement the stochastic evolution of a curve. First. we explain why great care should be taken when considering such an evolution in a level set framework. To guarantee the well-posedness of the evolution and to make it independent of the implicit representation of the initial curve, a Stratonovich differential has to be introduced. To implement this differential. a standard Ito plus drift approximation is proposed to turn an implicit scheme into an explicit one. Subsequently, we consider shape optimization techniques, which are a common framework to address various applications in computer vision, like segmentation, tracking, stereo vision etc. The objective of our approach is to improve these methods through the introduction of stochastic motion principles. The extension we propose can deal with local minima and with complex cases where the gradient of the objective function with respect to the shape is impossible to derive exactly. Finally. as an application. we focus on image segmentation methods, leading to what we call Stochastic Active Contours.

关键词： level sets stochastic partial differential equations shape optimization stochastic optimization segmentation active contours

来源：评论

学校读者我要写书评

暂无评论

Diffusion snakes:: Introducing statistical shape knowledge into the Mumford-Shah functional

引用

INTERNATIONAL JOURNAL OF computer vision 2002年第3期50卷 295-313页

作者： Cremers, D Tischhäuser, F Weickert, J Schnörr, C Univ Mannheim Dept Math & Comp Sci Comp Vis Graph & Pattern Recognit Grp D-68131 Mannheim Germany

We present a modification of the Mumford-Shah functional and its cartoon limit which facilitates the incorporation of a statistical prior on the shape of the segmenting contour. By minimizing a single energy functional, we obtain a segmentation process which maximizes both the grey value homogeneity in the separated regions and the similarity of the contour with respect to a set of training shapes. We propose a closed-form, parameter-free solution for incorporating invariance with respect to similarity transformations in the variational framework. We show segmentation results on artificial and real-world images with and without prior shape information. In the cases of noise, occlusion or strongly cluttered background the shape prior significantly improves segmentation. Finally we compare our results to those obtained by a level set implementation of geodesic active contours.

关键词： image segmentation shape recognition statistical learning variational methods diffusion snake geodesic active contours

来源：评论

学校读者我要写书评

暂无评论

On affine invariance in the Beltrami framework for vision

On affine invariance in the Beltrami framework for vision

引用

1st ieee workshop on variational and level set methods in computer vision

作者： Sochen, NA Tel Aviv Univ Dept Appl Math IL-69978 Tel Aviv Israel

ISBN: (纸本)076951278X

We use the geometric Beltrami framework to incorporate and explain some of the known invariant flows e.g. the equi-affine invariant flow. It is also demonstrated that the tint, concepts put forward in this framework enable us to construct new invariant flows for the case where the codimension is greater than one e.g. for color images and video.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast surface reconstruction using the level set method

Fast surface reconstruction using the level set method

引用

1st ieee workshop on variational and level set methods in computer vision

作者： Zhao, HK Osher, S Fedkiw, R Univ Calif Irvine Dept Math Irvine CA 92697 USA

ISBN: (纸本)076951278X

In this paper we describe new formulations and develop fast algorithms for implicit surface reconstruction based on variational and partial differential equation (PDE) methods. In particular we use the level set method and fast sweeping and tagging methods to reconstruct surfaces from scattered data set. The data set might consist of points, curves and/or surface patches. A weighted minimal surface-like model is constructed and its variational level set formulation is implemented with optimal efficiency. The reconstructed surface is smoother than piecewise linear and has a natural scaling in the regularization that allows varying flexibility according to the local sampling density. As is usual with the level set method we can handle complicated topology and deformations, as well as noisy or highly non-uniform data sets easily. The method is based on a simple rectangular arid, although adaptive and triangular grids are also possible. Some consequences, such as hole filling capability, are demonstrated, as well as the viability and convergence of our new fast tagging algorithm.

关键词： implicit surface partial differential equations variational formulation convection minimal surface

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：