Filters








21,191 Hits in 6.9 sec

Segmentation of Medical Images using Adaptively Regularized Kernel-based Fuzzy C-Means Clustering

Neha Tomar, Vyom Kulshreshtha, Pankaj Sharma
2019 International Journal of Computer Applications  
In this paper, we use a novel method to split brain tissues from magnetic resonance images, which routinely use regularized kernel-based fuzzy-clustering clusters.  ...  There are many drawbacks in existing methods based on soft clustering, which include low noise and high computational cost in the presence of image noise and artifacts.  ...  (2009) , which follows a different Physics analogy, but it is also based on a balancing criteria.  ... 
doi:10.5120/ijca2019918899 fatcat:mtaut4rwjzcstk3fexdb5emw3i

Dirichlet Graph Variational Autoencoder [article]

Jia Li, Tomasyu Yu, Jiajin Li, Honglei Zhang, Kangfei Zhao, YU Rong, Hong Cheng, Junzhou Huang
2020 arXiv   pre-print
Through experiments on graph generation and graph clustering, we demonstrate the effectiveness of our proposed framework.  ...  Our study connects VAEs based graph generation and balanced graph cut, and provides a new way to understand and improve the internal mechanism of VAEs based graph generation.  ...  Thus, it is reasonable to conclude that this regularization will help us to enforce a balanced graph cluster size.  ... 
arXiv:2010.04408v2 fatcat:uztnr6fpjncpbdz6ygomzj74w4

Normalized Cut Loss for Weakly-Supervised CNN Segmentation

Meng Tang, Abdelaziz Djelouah, Federico Perazzi, Yuri Boykov, Christopher Schroers
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Inspired by the general ideas in semi-supervised learning, we address these problems via a new principled loss function evaluating network output with criteria standard in "shallow" segmentation, e.g.  ...  We focus on normalized cut loss where dense Gaussian kernel is efficiently implemented in linear time by fast Bilateral filtering.  ...  This paper focuses on a popular balanced segmentation criterianormalized cut [43] . Our main contributions are: • We propose and evaluate a novel loss for weakly supervised semantic segmentation.  ... 
doi:10.1109/cvpr.2018.00195 dblp:conf/cvpr/TangDPBS18 fatcat:pv5cejmx5ba4tnqt3wgxc4l55m

Normalized Cut Loss for Weakly-supervised CNN Segmentation [article]

Meng Tang and Abdelaziz Djelouah and Federico Perazzi and Yuri Boykov and Christopher Schroers
2018 arXiv   pre-print
Inspired by the general ideas in semi-supervised learning, we address these problems via a new principled loss function evaluating network output with criteria standard in "shallow" segmentation, e.g.  ...  We focus on normalized cut loss where dense Gaussian kernel is efficiently implemented in linear time by fast Bilateral filtering.  ...  This paper focuses on a popular balanced segmentation criteria -normalized cut [43] . Our main contributions are: • We propose and evaluate a novel loss for weakly supervised semantic segmentation.  ... 
arXiv:1804.01346v1 fatcat:f3bjqinvarhaxl3543igaynzmi

ANIMC: A Soft Framework for Auto-weighted Noisy and Incomplete Multi-view Clustering [article]

Xiang Fang, Yuchong Hu, Pan Zhou, Dapeng Oliver Wu
2021 arXiv   pre-print
In this paper, we propose a novel Auto-weighted Noisy and Incomplete Multi-view Clustering framework (ANIMC) via a soft auto-weighted strategy and a doubly soft regular regression model.  ...  Firstly, by designing adaptive semi-regularized nonnegative matrix factorization (adaptive semi-RNMF), the soft auto-weighted strategy assigns a proper weight to each view and adds a soft boundary to balance  ...  In this paper, we propose a novel Auto-weighted Noisy and Incomplete Multi-view Clustering approach (ANIMC) via a soft auto-weighted strategy and a doubly soft regular regression model.  ... 
arXiv:2011.10331v3 fatcat:tcmr7sryq5eovmynlyir5ay4hy

Distributed Utilization Control for Real-Time Clusters with Load Balancing

Yong Fu, Hongan Wang, Chenyang Lu, Ramu Chandra
2006 2006 27th IEEE International Real-Time Systems Symposium (RTSS'06)  
This paper presents DUC-LB, a novel distributed utilization control algorithm for cluster-based soft real-time applications.  ...  Compared to earlier works on utilization control, a distinguishing feature of DUC-LB is its capability to handle system dynamics caused by load balancing, which is a common and essential component of most  ...  DUC-LB therefore can handle a more general workload model on real-time clusters.  ... 
doi:10.1109/rtss.2006.20 dblp:conf/rtss/FuWLC06 fatcat:inahsaut3vfs7kqg3bwk77pn7i

Gaussian Affinity for Max-Margin Class Imbalanced Learning

Munawar Hayat, Salman Khan, Syed Waqas Zamir, Jianbing Shen, Ling Shao
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
We hypothesize that improving the generalization capability of a classifier should improve learning on imbalanced datasets.  ...  Our approach is based on an 'affinity measure' in Euclidean space that leads to the following benefits: (1) direct enforcement of maximum margin constraints on classification boundaries, (2) a tractable  ...  To resolve this limitation, we introduce a novel multi-centered learning paradigm based on our max-margin framework.  ... 
doi:10.1109/iccv.2019.00657 dblp:conf/iccv/HayatKZS019 fatcat:r4zk7fwj7vac5n2z7pzxbp7xai

Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization [article]

Ozsel Kilinc, Ismail Uysal
2018 arXiv   pre-print
Due to the unsupervised objective based on Graph-based Activity Regularization (GAR) terms, softmax duplicates of each parent-class are specialized as the hidden information captured through the help of  ...  In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective.  ...  target distribution derived from the soft cluster assignments.  ... 
arXiv:1802.03063v1 fatcat:zqgvih6qvrhhzovt7w3oec4jyy

Minimum Conditional Entropy Clustering: A Discriminative Framework for Clustering

Bo Dai, Bao-Gang Hu
2010 Journal of machine learning research  
The proposed framework provides a unified perspective of Maximum Margin Clustering (MMC), Discriminative k -means, Spectral Clustering and Unsupervised Renyi's Entropy Analysis and also leads to a novel  ...  We propose an informationtheoretic framework as an implementation of the low-density separation assumption.  ...  Corollary 2 Spectral Clustering and Discriminative k-means can be obtained based on our framework.  ... 
dblp:journals/jmlr/DaiH10 fatcat:37ri5nh7rjflnnuv4prjsqaoxq

Multi-Granularity Regularized Re-Balancing for Class Incremental Learning [article]

Huitong Chen, Yu Wang, Qinghua Hu
2022 arXiv   pre-print
The multi-granularity regularization then transforms the one-hot label vector into a continuous label distribution, which reflects the relations between the target class and other classes based on the  ...  To this end, we further design a novel multi-granularity regularization term that enables the model to consider the correlations of classes in addition to re-balancing the data.  ...  In this paper, we propose a novel method, Multi-Granularity Regularized re-Balancing (MGRB), to address the problem of data imbalance based on a common knowledge distillation baseline.  ... 
arXiv:2206.15189v1 fatcat:522k5mpqijgvbawqgthf5srntu

A Novel Hybrid Transfer Learning Framework for Dynamic Cutterhead Torque Prediction of the Tunnel Boring Machine

Tao Fu, Tianci Zhang, Xueguan Song
2022 Energies  
In this study, a novel hybrid transfer learning framework, namely TRLS-SVR, is proposed to transfer knowledge from a historical dataset that may contain multiple working patterns and alleviate fresh data  ...  A collection of in situ TBM operation data from a tunnel project located in China is utilized to evaluate the performance of the proposed framework.  ...  Herein, a novel hybrid data-mining framework based on clustering, multitask learning (MTL), transfer learning, and least-squares support vector regression machines (LS-SVR), abbreviated as TRLS-SVR, is  ... 
doi:10.3390/en15082907 doaj:692631c51e044429a776c10ba9215b66 fatcat:qjnkvbukabfexhex3shvjufntm

Deep Fair Clustering for Visual Learning

Peizhao Li, Han Zhao, Hongfu Liu
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Existing work attempts to address this problem by reducing it to a classical balanced clustering with a constraint on the proportion of protected subgroups of the input space.  ...  methods on both cluster validity and fairness criterion.  ...  Clustering Regularizer. Inspired by other deep clustering [5, 6] , we employ a clustering regularizer to strengthen the predicted confidence and prevent large clusters.  ... 
doi:10.1109/cvpr42600.2020.00909 dblp:conf/cvpr/LiZL20 fatcat:h4jie5krojfjvnp7qjhyynhiiq

Max-margin Class Imbalanced Learning with Gaussian Affinity [article]

Munawar Hayat, Salman Khan, Waqas Zamir, Jianbing Shen, Ling Shao
2019 arXiv   pre-print
We hypothesize that improving the generalization capability of a classifier should improve learning on imbalanced datasets.  ...  Our approach is based on an 'affinity measure' in Euclidean space that leads to the following benefits: (1) direct enforcement of maximum margin constraints on classification boundaries, (2) a tractable  ...  To resolve this limitation, we introduce a novel multi-centered learning paradigm based on our max-margin framework.  ... 
arXiv:1901.07711v1 fatcat:ex4w7x4vqndxbmgcrue4s2ty3q

Deep Unsupervised Clustering Using Mixture of Autoencoders [article]

Dejiao Zhang, Yifan Sun, Brian Eriksson, Laura Balzano
2017 arXiv   pre-print
Unsupervised clustering is one of the most fundamental challenges in machine learning.  ...  A popular hypothesis is that data are generated from a union of low-dimensional nonlinear manifolds; thus an approach to clustering is identifying and separating these manifolds.  ...  This is based on the assumption that data from each cluster is generated from a separate low-dimensional manifold, and thus the aggregate data is modeled as a mixture of manifolds.  ... 
arXiv:1712.07788v2 fatcat:pwuarraobjg4bk5hzzwokklw4m

Multi-level Consistency Learning for Semi-supervised Domain Adaptation [article]

Zizheng Yan, Yushuang Wu, Guanbin Li, Yipeng Qin, Xiaoguang Han, Shuguang Cui
2022 arXiv   pre-print
a consistency-based self-training.  ...  compact target feature representations by proposing a novel class-wise contrastive clustering loss; (iii) at sample level, we follow standard practice and improve the prediction accuracy by conducting  ...  consistency learning method consists of a novel mapping and clustering strategy, and a novel prototype-based optimal transport method, which yields more robust and accurate domain alignment. (3) Our intra-domain  ... 
arXiv:2205.04066v3 fatcat:4l65qasp4jdfrjxmpmhm3fo4bq
« Previous Showing results 1 — 15 out of 21,191 results