paper-with-me

홈 › Papers

Discriminative Clustering with Representation Learning with any Ratio of Labeled to Unlabeled Data

2019-12-30 · Corinne Jones, Vincent Roulet, Zaid Harchaoui

We present a discriminative clustering approach in which the feature representation can be learned from data and moreover leverage labeled data. Representation learning can give a similarity-based clustering method the ability to automatically adapt to an underlying, yet hidden, geometric structure of the data. The proposed approach augments the DIFFRAC method with a representation learning capability, using a gradient-based stochastic training algorithm and an optimal transport algorithm with entropic regularization to perform the cluster assignment step. The resulting method is evaluated on several real datasets when varying the ratio of labeled data to unlabeled data and thereby interpolating between the fully unsupervised regime and the fully supervised regime. The experimental results suggest that the proposed method can learn powerful feature representations even in the fully unsupervised regime and can leverage even small amounts of labeled data to improve the feature representations and to obtain better clusterings of complex datasets.

📄 PDF Abstract BibTeX arXiv:1912.12979

Code (1)

cjones6/xsdc 공식 구현 pytorch

Tasks

ClusteringRepresentation Learning

Similar Papers 제목 키워드 기반

Generalized Category Discovery with Clustering Assignment Consistency

2023-10-30 · Xiangli Yang, Xinglin Pan, Irwin King, Zenglin Xu

Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using in…

ClusteringCommunity DetectionFine-Grained Visual RecognitionRepresentation Learning

Neighborhood Contrastive Learning for Novel Class Discovery

2021-06-20 · CVPR 2021 1 · Zhun Zhong, Enrico Fini, Subhankar Roy, Zhiming Luo 외

In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes. We exploit the peculiarities of NCD to build a new framew…

ClusteringContrastive LearningNovel Class Discovery

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

2021-04-19 · CVPR 2021 1 · Jichang Li, Guanbin Li, Yemin Shi, Yizhou Yu

In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them. However, the trained model cannot produce a highly discr…

ClusteringDomain AdaptationSemi-supervised Domain Adaptation

Discriminative Clustering for Robust Unsupervised Domain Adaptation

2019-05-30 · Rui Wang, Guoyin Wang, Ricardo Henao

Unsupervised domain adaptation seeks to learn an invariant and discriminative representation for an unlabeled target domain by leveraging the information of a labeled source dataset. We propose to improve the discriminat…

ClusteringDomain AdaptationPartial Domain AdaptationUnsupervised Domain Adaptation

Cluster Alignment with a Teacher for Unsupervised Domain Adaptation

2019-03-24 · ICCV 2019 10 · Zhijie Deng, Yucen Luo, Jun Zhu

Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. However, suc…

ClusteringDomain AdaptationUnsupervised Domain Adaptation