Image Clustering using an Augmented Generative Adversarial Network and
Information Maximization
- URL: http://arxiv.org/abs/2011.04094v1
- Date: Sun, 8 Nov 2020 22:20:33 GMT
- Title: Image Clustering using an Augmented Generative Adversarial Network and
Information Maximization
- Authors: Foivos Ntelemis, Yaochu Jin, Spencer A. Thomas
- Abstract summary: We propose a deep clustering framework consisting of a modified generative adversarial network (GAN) and an auxiliary classifier.
The proposed method significantly outperforms state-of-the-art clustering methods on CIFAR-10 and CIFAR-100, and is competitive on the STL10 and MNIST datasets.
- Score: 9.614694312155798
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Image clustering has recently attracted significant attention due to the
increased availability of unlabelled datasets. The efficiency of traditional
clustering algorithms heavily depends on the distance functions used and the
dimensionality of the features. Therefore, performance degradation is often
observed when tackling either unprocessed images or high-dimensional features
extracted from processed images. To deal with these challenges, we propose a
deep clustering framework consisting of a modified generative adversarial
network (GAN) and an auxiliary classifier. The modification employs Sobel
operations prior to the discriminator of the GAN to enhance the separability of
the learned features. The discriminator is then leveraged to generate
representations as the input to an auxiliary classifier. An adaptive objective
function is utilised to train the auxiliary classifier for clustering the
representations, aiming to increase the robustness by minimizing the divergence
of multiple representations generated by the discriminator. The auxiliary
classifier is implemented with a group of multiple cluster-heads, where a
tolerance hyper-parameter is used to tackle imbalanced data. Our results
indicate that the proposed method significantly outperforms state-of-the-art
clustering methods on CIFAR-10 and CIFAR-100, and is competitive on the STL10
and MNIST datasets.
Related papers
- Dynamic Clustering and Cluster Contrastive Learning for Unsupervised
Person Re-identification [29.167783500369442]
Unsupervised Re-ID methods aim at learning robust and discriminative features from unlabeled data.
We propose a dynamic clustering and cluster contrastive learning (DCCC) method.
Experiments on several widely used public datasets validate the effectiveness of our proposed DCCC.
arXiv Detail & Related papers (2023-03-13T01:56:53Z) - Improved Dual Correlation Reduction Network [40.792587861237166]
We propose a novel deep graph clustering algorithm termed Improved Dual Correlation Reduction Network (IDCRN)
By approximating the cross-view feature correlation matrix to an identity matrix, we reduce the redundancy between different dimensions of features.
We also avoid the collapsed representation caused by the over-smoothing issue in Graph Convolutional Networks (GCNs) through an introduced propagation regularization term.
arXiv Detail & Related papers (2022-02-25T07:48:32Z) - Deep clustering with fusion autoencoder [0.0]
Deep clustering (DC) models capitalize on autoencoders to learn intrinsic features which facilitate the clustering process in consequence.
In this paper, a novel DC method is proposed to address this issue. Specifically, the generative adversarial network and VAE are coalesced into a new autoencoder called fusion autoencoder (FAE)
arXiv Detail & Related papers (2022-01-11T07:38:03Z) - Attention-driven Graph Clustering Network [49.040136530379094]
We propose a novel deep clustering method named Attention-driven Graph Clustering Network (AGCN)
AGCN exploits a heterogeneous-wise fusion module to dynamically fuse the node attribute feature and the topological graph feature.
AGCN can jointly perform feature learning and cluster assignment in an unsupervised fashion.
arXiv Detail & Related papers (2021-08-12T02:30:38Z) - 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) - Channel DropBlock: An Improved Regularization Method for Fine-Grained
Visual Classification [58.07257910065007]
Existing approaches mainly tackle this problem by introducing attention mechanisms to locate the discriminative parts or feature encoding approaches to extract the highly parameterized features in a weakly-supervised fashion.
In this work, we propose a lightweight yet effective regularization method named Channel DropBlock (CDB) in combination with two alternative correlation metrics, to address this problem.
arXiv Detail & Related papers (2021-06-07T09:03:02Z) - Graph Contrastive Clustering [131.67881457114316]
We propose a novel graph contrastive learning framework, which is then applied to the clustering task and we come up with the Graph Constrastive Clustering(GCC) method.
Specifically, on the one hand, the graph Laplacian based contrastive loss is proposed to learn more discriminative and clustering-friendly features.
On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments.
arXiv Detail & Related papers (2021-04-03T15:32:49Z) - Adversarial Feature Augmentation and Normalization for Visual
Recognition [109.6834687220478]
Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models.
Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings.
We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
arXiv Detail & Related papers (2021-03-22T20:36:34Z) - Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain
Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain.
We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one.
Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
arXiv Detail & Related papers (2020-12-08T08:52:00Z) - Dual Adversarial Auto-Encoders for Clustering [152.84443014554745]
We propose Dual Adversarial Auto-encoder (Dual-AAE) for unsupervised clustering.
By performing variational inference on the objective function of Dual-AAE, we derive a new reconstruction loss which can be optimized by training a pair of Auto-encoders.
Experiments on four benchmarks show that Dual-AAE achieves superior performance over state-of-the-art clustering methods.
arXiv Detail & Related papers (2020-08-23T13:16:34Z) - AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive
Person Re-identification [0.0]
This paper presents a novel augmented discriminative clustering technique that estimates and augments person clusters in target domains.
AD-Cluster is trained by iterative density-based clustering, adaptive sample augmentation, and discriminative feature learning.
Experiments over Market-1501 and DukeMTMC-reID show that AD-Cluster outperforms the state-of-the-art with large margins.
arXiv Detail & Related papers (2020-04-19T07:34:37Z)
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.