Deep Clustering for Unsupervised Learning of Visual Features

2018-07-15 · ECCV 2018 9 · Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze

Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end training of visual features on large scale datasets. In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features. DeepCluster iteratively groups the features with a standard clustering algorithm, k-means, and uses the subsequent assignments as supervision to update the weights of the network. We apply DeepCluster to the unsupervised training of convolutional neural networks on large datasets like ImageNet and YFCC100M. The resulting model outperforms the current state of the art by a significant margin on all the standard benchmarks.

📄 PDF Abstract BibTeX arXiv:1807.05520

Code (9)

facebookresearch/deepcluster 공식 구현 pytorch

461054993/SDCN pytorch

Confusezius/selfsupervised_learning pytorch

ananyahjha93/swav pytorch

asanakoy/deep_clustering pytorch

bdy9527/SDCN pytorch

betashort/DeepClusterings pytorch

hsfzxjy/swavx pytorch

vinhdv1628/image_classification_task pytorch

Tasks

ClusteringDeep Clustering Image Clustering Self-Supervised Image Classification Semantic Segmentation Unsupervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

DeepCluster DeepCluster is a self-supervision approach for learning image representations. DeepCluster iteratively groups the features with a standard clustering algorithm, k-means, and…

Cluster Contrast for Unsupervised Visual Representation Learning

2025-07-16 · Nikolaos Giakoumoglou, Tania Stathaki arxiv

We introduce Cluster Contrast (CueCo), a novel approach to unsupervised visual representation learning that effectively combines the strengths of contrastive learning and clustering methods. Inspired by recent advancemen…

Representation Learning Contrastive Learning

Online Deep Clustering with Video Track Consistency

2022-06-07 · Alessandra Alfani, Federico Becattini, Lorenzo Seidenari, Alberto del Bimbo

Several unsupervised and self-supervised approaches have been developed in recent years to learn visual features from large-scale unlabeled datasets. Their main drawback however is that these methods are hardly able to r…

Clustering Deep Clustering Object

Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space

2022-10-21 · European Conference on Computer Vision 2022 10 · Shuo Li, Fang Liu, Zehua Hao, Kaibo Zhao 외

Most few-shot image classification methods are trained based on tasks. Usually, tasks are built on base classes with a large number of labeled images, which consumes large effort. Unsupervised few-shot image classificati…

Classification Clustering Few-Shot Image Classification image-classification+2

Deep Temporal Clustering: Fully unsupervised learning of time-domain features

2018-01-01 · ICLR 2018 1 · Naveen Sai Madiraju, Seid M. Sadat, Dimitry Fisher, Homa Karimabadi

Unsupervised learning of timeseries data is a challenging problem in machine learning. Here, we propose a novel algorithm, Deep Temporal Clustering (DTC), a fully unsupervised method, to naturally integrate dimensionali…

Clustering Dimensionality Reduction

Deep Temporal Clustering : Fully Unsupervised Learning of Time-Domain Features

2018-02-04 · Naveen Sai Madiraju, Seid M. Sadat, Dimitry Fisher, Homa Karimabadi

Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning. Here we propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimens…

Clustering Dimensionality Reduction Time Series Time Series Analysis