A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture

Min, Erxue; Guo, Xifeng; Liu, Qiang; Zhang, Gen; Cui, Jianjing; Long, Jun

doi:10.1109/access.2018.2855437

Cited by 416 publications

(276 citation statements)

References 32 publications

Supporting

Mentioning

267

Contrasting

Unclassified

Order By: Relevance

“…Many works in deep image clustering have achieved remarkable results or have become important approaches in how to handle the clustering problem [9]. All of these methods are directly related to our proposal.…”

Section: Related Workmentioning

confidence: 93%

Improving Deep Image Clustering with Spatial Transformer Layers

Souza

Zanchettin

2019

Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series

View full text Add to dashboard Cite

Image clustering is an important but challenging task in machine learning. As in most image processing areas, the latest improvements came from models based on the deep learning approach. However, classical deep learning methods have problems to deal with spatial image transformations like scale and rotation. In this paper, we propose the use of visual attention techniques to reduce this problem in image clustering methods. We evaluate the combination of a deep image clustering model called Deep Adaptive Clustering (DAC) with the Spatial Transformer Networks (STN). The proposed model is evaluated in the datasets MNIST and FashionMNIST and outperformed the baseline model.

show abstract

Section: Related Workmentioning

confidence: 93%

Improving Deep Image Clustering with Spatial Transformer Layers

Souza

Zanchettin

2019

Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series

View full text Add to dashboard Cite

show abstract

“…Clustering is not a new concept. Sev-eral classical [20] and deep learning-based [21] methods have been proposed. Classical clustering approaches are applied on relevant features extracted from the data [22].…”

Section: Dataset and Related Workmentioning

confidence: 99%

Learning Eating Environments Through Scene Clustering

Yarlagadda

Baireddy

Güera

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

It is well known that dietary habits have a significant influence on health. While many studies have been conducted to understand this relationship, little is known about the relationship between eating environments and health. Yet researchers and health agencies around the world have recognized the eating environment as a promising context for improving diet and health. In this paper, we propose an image clustering method to automatically extract the eating environments from eating occasion images captured during a community dwelling dietary study. Specifically, we are interested in learning how many different environments an individual consumes food in. Our method clusters images by extracting features at both global and local scales using a deep neural network. The variation in the number of clusters and images captured by different individual makes this a very challenging problem. Experimental results show that our method performs significantly better compared to several existing clustering approaches.

show abstract

“…Deep clustering is usually performed on the observations (input space) [25], but-may also be applied on the latent (intermediary) representation space [16,7,41,6,18,42,26]. The options for the clustering loss are numerous: k-means loss [40], cluster assignment hardening [39], locality-preserving loss [16], cluster classification loss [15] or agglomerative clustering loss [41] to cite a few.…”

Section: Related Workmentioning

confidence: 99%

Deep Unsupervised System Log Monitoring

Nourtel

Cerisara

Cruz‐Lara

2019

Product-Focused Software Process Improvement

View full text Add to dashboard Cite

This work proposes a new unsupervised deep generative model for system logs. It is designed to be generic and may be used in various downstream anomaly detection tasks, such as system failure or intrusion detection. It is based on the (reasonable) assumption that most log lines follow rather fixed syntactic structures, which enables us to replace the costly traditional convolutional and recurrent architectures by a much faster component: a deep averaging network. Our model still exploits a standard recurrent model with attention to capture the dependencies between successive log lines. We experimentally validate the proposed generative model on a real dataset obtained from a state-of-the-art High Performance Computing cluster and show the effectiveness of the proposed approach in modeling the "normal" behaviour of the system.

show abstract

A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture

Cited by 416 publications

References 32 publications

Improving Deep Image Clustering with Spatial Transformer Layers

Improving Deep Image Clustering with Spatial Transformer Layers

Learning Eating Environments Through Scene Clustering

Deep Unsupervised System Log Monitoring

Contact Info

Product

Resources

About