arXiv 1306.10832013-06-05cs.CVcs.LG

Discriminative Parameter Estimation for Random Walks Segmentation: Technical Report

École Centrale Paris（巴黎中央理工学院）；Université Paris-Est（巴黎东部大学）；École des Ponts ParisTech（巴黎路桥学院）；INRIA Saclay（法国国家信息与自动化研究所萨克莱分院）；Institute of Myology（肌病学研究所）；CEA（法国原子能和替代能源委员会）；UPMC University Paris 06（巴黎第六大学）

Pierre-Yves Baudin, Danny Goodman, Puneet Kumar, Noura Azzabou, Pierre G. Carlier, Nikos Paragios, M. Pawan Kumar

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

The Random Walks (RW) algorithm is one of the most e - cient and easy-to-use probabilistic segmentation methods. By combining contrast terms with prior terms, it provides accurate segmentations of medical images in a fully automated manner. However, one of the main drawbacks of using the RW algorithm is that its parameters have to be hand-tuned. we propose a novel discriminative learning framework that estimates the parameters using a training dataset. The main challenge we face is that the training samples are not fully supervised. Speci cally, they provide a hard segmentation of the images, instead of a proba-bilistic segmentation. We overcome this challenge by treating the optimal probabilistic segmentation that is compatible with the given hard segmentation as a latent variable. This allows us to employ the latent support vector machine formulation for parameter estimation. We show that our approach signi cantly outperforms the baseline methods on a challenging dataset consisting of real clinical 3D MRI volumes of skeletal muscles.

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

Discriminative Parameter Estimation for Random Walks Segmentation

École Centrale Paris（巴黎中央理工学院）；Université Paris-Est（巴黎东大学）；École des Ponts ParisTech（巴黎高科桥路学院）；INRIA Saclay（法国国家信息与自动化研究所萨克雷中心）；Institute of Myology（肌病学研究所）；CEA（法国原子能和替代能源委员会）；UPMC University Paris 06（巴黎第六大学（UPMC））

2013-08-30cs.CVcs.LG

D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation

Stanford University（斯坦福大学）

We address weakly supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D3TW), the first discriminative model using weak ordering supervision. The key technical challenge for discriminative modeling with weak supervision is that the loss function of the ordering supervision is usually formulated using dynamic programming and is thus not differentiable. We address this challenge with a continuous relaxation of the min-operator in dynamic programming and extend…

2019-04-11cs.CV

Colorectal Cancer Outcome Prediction from H&E Whole Slide Images using Machine Learning and Automatically Inferred Phenotype Profiles

School of Computer Science（计算机科学学院）；School of Medicine（医学院）；University of St Andrews（圣安德鲁斯大学）

Digital pathology (DP) is a new research area which falls under the broad umbrella of health informatics. Owing to its potential for major public health impact, in recent years DP has been attracting much research attention. Nevertheless, a wide breadth of significant conceptual and technical challenges remain, few of them greater than those encountered in the field of oncology. The automatic analysis of digital pathology slides of cancerous tissues is particularly problematic due to the inherent heterogeneity of the disease, extremely large images, amongst numerous others. In this paper we in…

2019-03-09cs.CVeess.IV

A Technical Report for ICCV 2021 VIPriors Re-identification Challenge

NetEase Games AI Lab（网易游戏人工智能实验室）

Person re-identification has always been a hot and challenging task. This paper introduces our solution for the re-identification track in VIPriors Challenge 2021. In this challenge, the difficulty is how to train the model from scratch without any pretrained weight. In our method, we show use state-of-the-art data processing strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. (1) Both image augmentation strategy and novel pre-processing method for occluded images can help the model learn mo…

2021-09-30cs.CV

Weakly Supervised Action Labeling in Videos Under Ordering Constraints

INRIA（法国国家信息与自动化研究所）；École Normale Supérieure（巴黎高等师范学院）

We are given a set of video clips, each one annotated with an {\em ordered} list of actions, such as "walk" then "sit" then "answer phone" extracted from, for example, the associated text script. We seek to temporally localize the individual actions in each clip as well as to learn a discriminative classifier for each action. We formulate the problem as a weakly supervised temporal assignment with ordering constraints. Each video clip is divided into small time intervals and each time interval of each video clip is assigned one action label, while respecting the order in which the action label…

2014-07-04cs.CVcs.LG

Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)

University of Chinese Academy of Sciences（中国科学院大学）；Bytedance Inc.（字节跳动公司）

This report presents the approach used in the submission of Generic Event Boundary Detection (GEBD) Challenge at CVPR21. In this work, we design a Cascaded Temporal Attention Network (CASTANET) for GEBD, which is formed by three parts, the backbone network, the temporal attention module, and the classification module. Specifically, the Channel-Separated Convolutional Network (CSN) is used as the backbone network to extract features, and the temporal attention module is designed to enforce the network to focus on the discriminative features. After that, the cascaded architecture is used in the …

2021-07-01cs.CV

更多相关论文收起更多论文

Enhancing Social Relation Inference with Concise Interaction Graph and Discriminative Scene Representation

Intellifusion（云天励飞）；Peking University（北京大学）

There has been a recent surge of research interest in attacking the problem of social relation inference based on images. Existing works classify social relations mainly by creating complicated graphs of human interactions, or learning the foreground and/or background information of persons and objects, but ignore holistic scene context. The holistic scene refers to the functionality of a place in images, such as dinning room, playground and office. In this paper, by mimicking human understanding on images, we propose an approach of \textbf{PR}actical \textbf{I}nference in \textbf{S}ocial r\te…

2021-07-30cs.AIcs.CV

Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk

Nanyang Technological University（南洋理工大学）

Due to the scarcity of annotated scene flow data, self-supervised scene flow learning in point clouds has attracted increasing attention. In the self-supervised manner, establishing correspondences between two point clouds to approximate scene flow is an effective approach. Previous methods often obtain correspondences by applying point-wise matching that only takes the distance on 3D point coordinates into account, introducing two critical issues: (1) it overlooks other discriminative measures, such as color and surface normal, which often bring fruitful clues for accurate matching; and (2) i…

2021-05-18cs.CV

图像生成模型：技术史

Image Generation Models: A Technical History

本文综述了过去十年图像生成模型的快速发展，涵盖VAEs、GANs、正常化流、自回归和Transformer模型以及扩散方法，分析其技术原理、训练方法及局限性，并讨论视频生成和模型鲁棒性等最新进展。

2026-03-29cs.AIcs.CLcs.CV

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation

DGIST（韩国基础科学研究院）；POSTECH（浦项科技大学）

The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class labels. In this weakly supervised setting, trained models have been known to segment local discriminative parts rather than the entire object area. Our solution is to propagate such local responses to nearby areas which belong to the same semantic entity. To this end, we propose a Deep Neural Network (DNN) called AffinityNet that predicts semantic affinity between…

2018-04-09cs.CV

SD-DiT：在Diffusion Transformer中释放自监督判别的能力

SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer

The Chinese University of HongKong, Shenzhen（香港中文大学（深圳））；HiDream.ai Inc.（希迪人工智能公司）；The Hong Kong Polytechnic University（香港理工大学）

本文提出SD-DiT，通过引入自监督判别知识并以教师-学生模式构建基于PF-ODE的判别对，解耦DiT编码器与解码器分别处理判别与生成目标，有效解决了掩码策略的局限，在ImageNet上实现了训练成本与生成能力的良好平衡。

2024-03-25cs.CVcs.MM