Open AccessPosted Content
Consensus Clustering With Unsupervised Representation Learning.
TL;DR: This work proposes a novel ensemble learning algorithm dubbed Consensus Clustering with Unsupervised Representation Learning (ConCURL) which learns representations by creating a consensus on multiple clustering outputs and outperforms all state of the art methods on various computer vision datasets.
read more
Abstract: Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the representation space, or have a similar cluster assignment. Bootstrap Your Own Latent (BYOL) is one such representation learning algorithm that has achieved state-of-the-art results in self-supervised image classification on ImageNet under the linear evaluation protocol. However, the utility of the learnt features of BYOL to perform clustering is not explored. In this work, we study the clustering ability of BYOL and observe that features learnt using BYOL may not be optimal for clustering. We propose a novel consensus clustering based loss function, and train BYOL with the proposed loss in an end-to-end way that improves the clustering ability and outperforms similar clustering based methods on some popular computer vision datasets.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization
TL;DR: In this article, a multi-level feature optimization framework is proposed to improve the generalization and temporal modeling ability of learned video representations, where high-level features obtained from naive and prototypical contrastive learning are utilized to build distribution graphs, guiding the process of low-level and midlevel feature learning.
29
Deep Clustering With Consensus Representations
Lukas Miklautz,Martin Teuffenbach,Pascal Weber,Rona Perjuci,Walid Durani,Christian Böhm,Claudia Plant +6 more
- 13 Oct 2022
TL;DR: The idea of learning consensus representations for heterogeneous clusterings, a novel notion to approach consensus clustering, is introduced and DECCS, the first deep clustering method that jointly improves the representation and clustering results of multiple heterogeneous clustering algorithms is proposed.
5
On Challenges in Unsupervised Domain Generalization
TL;DR: Unsupervised domain generalization (UDG) as discussed by the authors aims to learn a model from an unlabeled set of source domains that can semantically cluster images in an unseen target domain.
4
GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning
Huseyin Coskun,Alireza Zareian,Josh L. Moore,Federico Tombari,Chen Wang +4 more
- 20 Jul 2022
TL;DR: This paper proposes a principled way to combine two views where the initial cluster assignment of each view is used as prior to guide the final cluster assignments of the other view, and a novel regularization strategy is proposed to address the feature collapse problem.
2
Enhancing Clustering Representations with Positive Proximity and Cluster Dispersion Learning
Abhishek Kumar,Dong Gyu Lee +1 more
TL;DR: PIPCDR excels in producing well-separated clusters, generating uniform representations, avoiding class collision issues, and enhancing within-cluster compactness, demonstrating its competitive performance on moderate-scale clustering benchmark datasets and establishing new state-of-the-art results on large-scale datasets.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
•Posted Content
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.
82.5K
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
•Dissertation
Learning Multiple Layers of Features from Tiny Images
Alex Krizhevsky
- 01 Jan 2009
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.