RESEARCH

COMPUTER VISION

Deep Clustering for Unsupervised Learning of Visual Features

September 09, 2018

Abstract

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.

Download the Paper

AUTHORS

Written by

Piotr Bojanowski

Armand Joulin

Matthijs Douze

Mathilde Caron

Publisher

ECCV

Research Topics

Computer Vision

Related Publications

June 04, 2023

COMPUTER VISION

Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation

Dahyun Kang, Peter Koniusz, Minsu Cho, Naila Murray

June 04, 2023

May 09, 2023

COMPUTER VISION

ImageBind: One Embedding Space To Bind Them All

Rohit Girdhar, Alaa El-Nouby, Zhuang Liu, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, Ishan Misra

May 09, 2023

April 20, 2023

COMPUTER VISION

SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision

Xubo Liu, Egor Lakomkin, Dino Vougioukas, Pingchuan Ma, Honglie Chen, Ruiming Xie, Morrie Doulaty, Niko Moritz, Jachym Kolar, Stavros Petridis, Maja Pantic, Christian Fuegen

April 20, 2023

April 06, 2023

COMPUTER VISION

On the Benefits of 3D Pose and Tracking for Human Action Recognition

Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Christoph Feichtenhofer, Jitendra Malik

April 06, 2023

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.