methodology-6

Deep Clustering

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in deep-clustering-20

Trend

Dataset

Best Model

Actions

Stackoverflow

Searchsnippets

MNIST

Libraries

i

Use these libraries to find deep-clustering-20 models and implementations

mpariente/asteroid

2 papers 2,096

Datasets

MNIST

USPS

Subtasks

Trajectory Clustering NONPARAMETRIC DEEP CLUSTERING Deep Nonparametric Clustering

Most implemented papers

Deep Clustering for Unsupervised Learning of Visual Features

Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze•Sat Jul 14 2018

This work presents DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features and outperforms the current state of the art by a significant margin on all the standard benchmarks.

2126

Content

USPS

Coil-20

0

Paper Graph

Deep clustering: Discriminative embeddings for segmentation and separation

Jonathan Le Roux, J. Hershey, Shinji Watanabe, Zhuo Chen•Mon Aug 17 2015

Preliminary experiments on single-channel mixtures from multiple speakers show that a speaker-independent model trained on two-speaker mixtures can improve signal quality for mixtures of held-out speakers by an average of 6dB, and the same model does surprisingly well with three-speakers mixtures.

1409 0

Paper Graph

N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding

I. Craddock, Ryan McConville, R. Piechocki, Raúl Santos-Rodríguez•Thu Aug 15 2019

This work quantitatively shows across a range of image and time-series datasets that the proposed method has competitive performance against the latest deep clustering algorithms, including outperforming current state-of-the-art on several.

124 0

Paper Graph

Single-Channel Multi-Speaker Separation Using Deep Clustering

Jonathan Le Roux, J. Hershey, Shinji Watanabe, Zhuo Chen, Y. Isik•Wed Jul 06 2016

This paper significantly improves upon the baseline system performance by incorporating better regularization, larger temporal context, and a deeper architecture, culminating in an overall improvement in signal to distortion ratio (SDR) of 10.3 dB compared to the baseline, and produces unprecedented performance on a challenging speech separation.

447 0

Paper Graph

DPSOM: Deep Probabilistic Clustering with Self-Organizing Maps

Matthias Hüser, G. Rätsch, Laura Manduchi, Vincent Fortuin•Wed Oct 02 2019

This work presents a novel way to fit self-organizing maps with probabilistic cluster assignments, PSOM, a new deep architecture for Probabilistic clustering, DPSOM, and its extension to time series data, T-DPSOM, which achieve superior clustering performance compared to current deep clustering methods on static MNIST/Fashion-MNIST data as well as medical time series, while also inducing an interpretable representation.

16 0

Paper Graph

Structural Deep Clustering Network

Peng Cui, Deyu Bo, Xiao Wang, C. Shi, Meiqi Zhu, Emiao Lu•Tue Feb 04 2020

A Structural Deep Clustering Network (SDCN) is proposed to integrate the structural information into deep clustering, with a delivery operator to transfer the representations learned by autoencoder to the corresponding GCN layer, and a dual self-supervised mechanism to unify these two different deep neural architectures and guide the update of the whole model.

593 0

Paper Graph

Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering

K. Jia, Hui Tang•Wed Mar 18 2020

This work describes the proposed method as Structurally Regularized Deep Clustering (SRDC), where it enhances target discrimination with clustering of intermediate network features, and enhance structural regularization with soft selection of less divergent source examples.

318 0

Paper Graph

Dissimilarity Mixture Autoencoder for Deep Clustering

Juan S. Lara, F. A. Gonz'alez•Sun Jun 14 2020

A novel neural network model that uses a dissimilarity function to generalize a family of density estimation and clustering methods and can leverage from deep representation learning due to its straightforward incorporation into deep learning architectures.

6 0

Paper Graph

Adding a benchmark result helps the community track progress.