Deep clustering with a Dynamic Autoencoder: From reconstruction towards centroids construction

Mrabah, Nairouz; Khan, Naimul; Ksantini, Riadh; Lachiri, Zied

doi:10.1016/j.neunet.2020.07.005

Cited by 65 publications

(30 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…clustering). In fact, Mrabah et al [13,14] show that the aforementioned IDEC suffers from OFM during training -supporting our hypothesis on OFM occurring in autoencoder-based deep clustering models.…”

Section: Introductionsupporting

confidence: 88%

Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective

Trosten

Jenssen

Kampffmeyer

2021

nldl

View full text Add to dashboard Cite

Preservation of local similarity structure is a key challenge in deep clustering. Many recent deep clustering methods therefore use autoencoders to help guide the model's neural network towards an embedding which is more reflective of the input space geometry. However, recent work has shown that autoencoder-based deep clustering models can suffer from objective function mismatch (OFM). In order to improve the preservation of local similarity structure, while simultaneously having a low OFM, we develop a new auxiliary objective function for deep clustering. Our Unsupervised Companion Objective (UCO) encourages a consistent clustering structure at intermediate layers in the network -- helping the network learn an embedding which is more reflective of the similarity structure in the input space. Since a clustering-based auxiliary objective has the same goal as the main clustering objective, it is less prone to introduce objective function mismatch between itself and the main objective. Our experiments show that attaching the UCO to a deep clustering model improves the performance of the model, and exhibits a lower OFM, compared to an analogous autoencoder-based model.

show abstract

Section: Introductionsupporting

confidence: 88%

Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective

Trosten

Jenssen

Kampffmeyer

2021

nldl

View full text Add to dashboard Cite

show abstract

“…It showed improvement in results from DEC [28]. The last method is Dynamic Autoencoder (DynAE) [29]. DynAE has a bit similar structure to the other two; however, its main contribution is the dynamic loss function.…”

Section: Related Workmentioning

confidence: 99%

“…The general idea of deep clustering consists of two stages; pretraining an autoencoder, which allows the network to learn features that are used to initialize the cluster centers [45], and fine-tuning, where clustering and feature learning are jointly performed [45]. The methods we will use for clustering are as mentioned before; DEC [26], IDEC [28], and DynAE [29].…”

Section: ) Deep Clustering Models (Unsupervised Learning)mentioning

confidence: 99%

See 1 more Smart Citation

A Classification of Arab Ethnicity Based on Face Image Using Deep Learning Approach

And

Prince

2021

IEEE Access

View full text Add to dashboard Cite

Human face and facial features gain a lot of attention from researchers and are considered as one of the most popular topics recently. Features and information extracted from a person are known as soft biometric, they have been used to improve the recognition performance and enhance the search engine for face images, which can be further applied in various fields such as law enforcement, surveillance videos, advertisement, and social media profiling. By observing relevant studies in the field, we noted a lack of mention of the Arab world and an absence of Arab dataset as well. Therefore, our aim in this paper is to create an Arab dataset with proper labeling of Arab sub-ethnic groups, then classify these labels using deep learning approaches. Arab image dataset that was created consists of three labels: Gulf Cooperation Council countries (GCC), the Levant, and Egyptian. Two types of learning were used to solve the problem. The first type is supervised deep learning (classification); a Convolutional Neural Network (CNN) pre-trained model has been used as CNN models achieved state of art results in computer vision classification problems. The second type is unsupervised deep learning (deep clustering). The aim of using unsupervised learning is to explore the ability of such models in classifying ethnicities. To our knowledge, this is the first time deep clustering is used for ethnicity classification problems. For this, three methods were chosen. The best result of training a pre-trained CNN on the full Arab dataset then evaluating on a different dataset was 56.97%, and 52.12% when Arab dataset labels were balanced. The methods of deep clustering were applied on different datasets, showed an ACC from 32% to 59%, and NMI and ARI result from zero to 0.2714 and 0.2543 respectively.

show abstract

“…Clustering as a classic unsupervised learning problem has been studied in many research works [84]- [91]. In recent years, deep learning based clustering studies [88], [89], [91]- [94] have been conducted due to favorable feature extraction capability of neural networks. Most algorithms in this category can simultaneously learn feature embeddings and cluster assignments.…”

Section: Clusteringmentioning

confidence: 99%

Deep feature learning for image classification via countering over-fitting

Qing¹

View full text Add to dashboard Cite

show abstract

Deep clustering with a Dynamic Autoencoder: From reconstruction towards centroids construction

Cited by 65 publications

References 28 publications

Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective

Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective

A Classification of Arab Ethnicity Based on Face Image Using Deep Learning Approach

Deep feature learning for image classification via countering over-fitting

Contact Info

Product

Resources

About