Deep Adaptive Image Clustering

Chang, Jianlong; Wang, Lingfeng; Meng, Guang; Xiang, Shiming; Chen, Pan

doi:10.1109/iccv.2017.626

Cited by 359 publications

(242 citation statements)

References 19 publications

Supporting

Mentioning

239

Contrasting

Unclassified

Order By: Relevance

“…Finally, the model cluster the images according to the most significant label features. The DAC reached the state-of-the-art in several public datasets [1].…”

Section: Deep Adaptive Clustering -Dacmentioning

confidence: 94%

“…To evaluate our hypothesis, we use the DAC* model, a more simple DAC version also presented in the original DAC paper [1]. In the DAC* the upper and lower sampler selection thresholds are set by the parameter λ that is added linearly at each epoch.…”

Section: Proposed Pipelinementioning

confidence: 99%

“…The original DAC [1] paper does not perform experiments in the Fashion MNIST dataset. For comparison purposes, we run the DAC* version in the Fashion MNIST and MNIST datasets using the same parameters suggested in the original paper.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…For a long time, classic techniques such as K-means were the best option to image clustering [13] [14]. In recent years, deep neural networks have proved to be very effective in several image processing areas and deep clustering approaches reached the state-of-the-art in manifold image benchmarks using methods such as Deep Clustering Network (DCN) [17], Joint Unsupervised Learning (JULE) arXiv:1902.05401v2 [cs.CV] 24 Oct 2019 [18], Deep Embbeded Cluster (DEC) [16], Deep Embbeded Cluster with Data Augmentation (DEC-DA) [4] and Deep Adaptive Clustering (DAC) [1].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

“…Finally, the model cluster the images according to the most significant label features. The DAC reached the state-of-the-art in several public datasets [1].…”

Section: Deep Adaptive Clustering -Dacmentioning

confidence: 94%

Section: Proposed Pipelinementioning

confidence: 99%

Section: Experimental Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

“…Inspired by the fact that deep convolutional neural networks can capture feature in a hierarchical way from a lowlevel to a high level, Chang et al [5] adopt the curriculum learning to adaptively select labeled samples for training convolutional neural networks and use a strategy to adaptively choose the label features defined by the cosine similarity. Yang et al [37] dispose of the successive cluster- Table 1.…”

Section: Related Workmentioning

confidence: 99%

Generative approach to unsupervised deep local learning

et al. 2019

View full text Add to dashboard Cite

Most existing feature learning methods optimize inflexible handcrafted features and the affinity matrix is constructed by shallow linear embedding methods. Different from these conventional methods, we pretrain a generative neural network by stacking convolutional autoencoders to learn the latent data representation and then construct an affinity graph with them as a prior. Based on the pretrained model and the constructed graph, we add a self-expressive layer to complete the generative model and then fine-tune it with a new loss function, including the reconstruction loss and a deliberately defined locality-preserving loss. The locality-preserving loss designed by the constructed affinity graph serves as prior to preserve the local structure during the fine-tuning stage, which in turn improves the quality of feature representation effectively. Furthermore, the self-expressive layer between the encoder and decoder is based on the assumption that each latent feature is a linear combination of other latent features, so the weighted combination coefficients of the self-expressive layer are used to construct a new refined affinity graph for representing the data structure. We conduct experiments on four datasets to demonstrate the superiority of the representation ability of our proposed model over the state-of-the-art methods.

show abstract

Unsupervised structural damage identification based on covariance matrix and deep clustering

Zhang,

Wang,

Zhao

et al. 2024

Structural Design Tall Build

View full text Add to dashboard Cite

SummaryStructural damage identification is a major task in structural health monitoring. Machine learning and deep learning algorithms have been widely applied in the research of structural damage identification. Supervised algorithms require expert labeling, making it difficult to implement in engineering applications. Unsupervised structural damage identification algorithms are generally divided into two parts: damage‐sensitive factor extraction and damage determination. Existing algorithms all perform these two steps separately. This paper proposes a damage identification method combining covariance matrix and improved deep embedding clustering network (IDEC). IDEC can perform damage‐sensitive factor extraction and damage determination operations at the same time. The covariance matrix that introduces delay information contains rich damage features, and the combination of the two has been proven to effectively mine the damage‐sensitive feature space. After network hyperparameter optimization via Bayesian optimization, the proposed method is applied to the damage identification and quantification using real bridge acceleration response data under vehicle load. The results show that this method can identify structural damage with an accuracy of up to 97% with better performance than existing technologies, and it also has great performance in identifying small damages. The proposed method is expected to increase the damage identification accuracy if applied in engineering practice.

show abstract

Deep Adaptive Image Clustering

Cited by 359 publications

References 19 publications

Improving Deep Image Clustering with Spatial Transformer Layers

Improving Deep Image Clustering with Spatial Transformer Layers

Generative approach to unsupervised deep local learning

Unsupervised structural damage identification based on covariance matrix and deep clustering

Contact Info

Product

Resources

About