Deep clustering using adversarial net based clustering loss
- URL: http://arxiv.org/abs/2412.08933v3
- Date: Wed, 05 Feb 2025 07:50:18 GMT
- Title: Deep clustering using adversarial net based clustering loss
- Authors: Kart-Leong Lim,
- Abstract summary: We reformulate deep clustering as an adversarial net over traditional closed form KL divergence.
We demonstrated the performance of our proposed method on several well cited datasets.
- Score: 0.65268245109828
- License:
- Abstract: Deep clustering is a recent deep learning technique which combines deep learning with traditional unsupervised clustering. At the heart of deep clustering is a loss function which penalizes samples for being an outlier from their ground truth cluster centers in the latent space. The probabilistic variant of deep clustering reformulates the loss using KL divergence. Often, the main constraint of deep clustering is the necessity of a closed form loss function to make backpropagation tractable. Inspired by deep clustering and adversarial net, we reformulate deep clustering as an adversarial net over traditional closed form KL divergence. Training deep clustering becomes a task of minimizing the encoder and maximizing the discriminator. At optimality, this method theoretically approaches the JS divergence between the distribution assumption of the encoder and the discriminator. We demonstrated the performance of our proposed method on several well cited datasets such as MNIST, REUTERS10K and CIFAR10, achieving on-par or better performance with some of the state-of-the-art deep clustering methods.
Related papers
- Deep Clustering using Dirichlet Process Gaussian Mixture and Alpha Jensen-Shannon Divergence Clustering Loss [0.65268245109828]
In the autoencoder based deep clustering, the challenge is how to jointly optimize both clustering and dimension reduction together.
We introduce an infinite cluster representation using Dirichlet process Gaussian mixture model for joint clustering and model selection in the latent space.
We evaluate our proposed deep model selection method with traditional model selection on large class number datasets such as MIT67 and CIFAR100.
arXiv Detail & Related papers (2024-12-12T05:02:41Z) - DivClust: Controlling Diversity in Deep Clustering [47.85350249697335]
DivClust produces consensus clustering solutions that consistently outperform single-clustering baselines.
Our method effectively controls diversity across frameworks and datasets with very small additional computational cost.
arXiv Detail & Related papers (2023-04-03T14:45:43Z) - Deep Clustering: A Comprehensive Survey [53.387957674512585]
Clustering analysis plays an indispensable role in machine learning and data mining.
Deep clustering, which can learn clustering-friendly representations using deep neural networks, has been broadly applied in a wide range of clustering tasks.
Existing surveys for deep clustering mainly focus on the single-view fields and the network architectures, ignoring the complex application scenarios of clustering.
arXiv Detail & Related papers (2022-10-09T02:31:32Z) - A Deep Dive into Deep Cluster [0.2578242050187029]
DeepCluster is a simple and scalable unsupervised pretraining of visual representations.
We show that DeepCluster convergence and performance depend on the interplay between the quality of the randomly filters of the convolutional layer and the selected number of clusters.
arXiv Detail & Related papers (2022-07-24T22:55:09Z) - DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep
Neural Networks [53.88811980967342]
This paper presents a Deep Clustering via Ensembles (DeepCluE) approach.
It bridges the gap between deep clustering and ensemble clustering by harnessing the power of multiple layers in deep neural networks.
Experimental results on six image datasets confirm the advantages of DeepCluE over the state-of-the-art deep clustering approaches.
arXiv Detail & Related papers (2022-06-01T09:51:38Z) - Augmented Data as an Auxiliary Plug-in Towards Categorization of
Crowdsourced Heritage Data [2.609784101826762]
We propose a strategy to mitigate the problem of inefficient clustering performance by introducing data augmentation as an auxiliary plug-in.
We train a variant of Convolutional Autoencoder (CAE) with augmented data to construct the initial feature space as a novel model for deep clustering.
arXiv Detail & Related papers (2021-07-08T14:09:39Z) - Deep Distribution-preserving Incomplete Clustering with Optimal
Transport [43.0056459311929]
We propose a novel deep incomplete clustering method, named Deep Distribution-preserving Incomplete Clustering with Optimal Transport (DDIC-OT)
The proposed network achieves superior and stable clustering performance improvement against existing state-of-the-art incomplete clustering methods over different missing ratios.
arXiv Detail & Related papers (2021-03-21T15:43:17Z) - Deep Clustering by Semantic Contrastive Learning [67.28140787010447]
We introduce a novel variant called Semantic Contrastive Learning (SCL)
It explores the characteristics of both conventional contrastive learning and deep clustering.
It can amplify the strengths of contrastive learning and deep clustering in a unified approach.
arXiv Detail & Related papers (2021-03-03T20:20:48Z) - Joint Optimization of an Autoencoder for Clustering and Embedding [22.16059261437617]
We present an alternative where the autoencoder and the clustering are learned simultaneously.
That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model.
arXiv Detail & Related papers (2020-12-07T14:38:10Z) - Overcomplete Deep Subspace Clustering Networks [80.16644725886968]
Experimental results on four benchmark datasets show the effectiveness of the proposed method over DSC and other clustering methods in terms of clustering error.
Our method is also not as dependent as DSC is on where pre-training should be stopped to get the best performance and is also more robust to noise.
arXiv Detail & Related papers (2020-11-16T22:07:18Z) - Scalable Hierarchical Agglomerative Clustering [65.66407726145619]
Existing scalable hierarchical clustering methods sacrifice quality for speed.
We present a scalable, agglomerative method for hierarchical clustering that does not sacrifice quality and scales to billions of data points.
arXiv Detail & Related papers (2020-10-22T15:58:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.