Dual Adversarial Autoencoders for Clustering

Ge, Pengfei; Ren, Chuan-Xian; Dai, Dao‐Qing; Feng, Jiashi; Yan, Shuicheng

doi:10.1109/tnnls.2019.2919948

Cited by 40 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The other is to evaluate the generated data through the classification scores of specific functions, such as inception score [35]. This type of method [36]- [39] evaluates on the basis of a specific pretrained model, without considering the effect of real data and lacking the authenticity evaluation of generated images.…”

Section: B Evaluation Methods and Indicator 1) Evaluation Methodsmentioning

confidence: 99%

ECGAN: An Improved Conditional Generative Adversarial Network With Edge Detection to Augment Limited Training Data for the Classification of Remote Sensing Images With High Spatial Resolution

Sui

Jiang

Zhang

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The classification of remote sensing images with high spatial resolution requires considerable training samples, but the process of sample making is slow and laborious. How to guarantee the accuracy of supervised classification under the condition of limited samples is an urgent problem to be solved in the field of supervised classification. For addressing this problem, we proposes an improved conditional generative adversarial network with edge feature (ECGAN) to augment limited training data for the classification of remote sensing images with high spatial resolution in this paper. On the basis of conditional generative adversarial network, feature factors of interclass boundaries and intraclass edges are added to networks, and an objective function with multiscale and multilevel features is constructed. The ISPRS Potsdam and Vaihingen remote sensing datasets are regarded as examples. Results indicate that the high-resolution remote sensing images generated by using the network proposed in this paper have abundant texture, accurate edges, and are highly similar to real images. The generated images are used to augment training samples, and an experiment for classifying high-resolution remote sensing images is conducted. The classification results of the proposed augmentation method perform better than that of the traditional sample augmentation method. We prove that ECGAN as a means of sample augmentation can effectively solves the problem that the classification effect is unideal when the supervised classification sample is insufficient.

show abstract

Section: B Evaluation Methods and Indicator 1) Evaluation Methodsmentioning

confidence: 99%

ECGAN: An Improved Conditional Generative Adversarial Network With Edge Detection to Augment Limited Training Data for the Classification of Remote Sensing Images With High Spatial Resolution

Sui

Jiang

Zhang

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Autoencoder (AE)-based methods employ encoders to project high-dimensional input molecules into lowdimensional representations and decoders to reconstruct the original inputs via these low-dimensional features. Enhanced by additional latent variables and discriminator neural networks [44], VAE-based [20], [27], and AAE-based [30], [31] approaches were proposed. Comprehensive work has been conducted where various AE models are compared and assessed [28].…”

Section: A Generative Model Of Moleculesmentioning

confidence: 99%

Graph Polish: A Novel Graph Generation Paradigm for Molecular Optimization

Zheng

Wang

et al. 2023

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Molecular optimization, which transforms a given input molecule X into another Y with desired properties, is essential in molecular drug discovery. The traditional approaches either suffer from sample-inefficient learning or ignore information that can be captured with the supervised learning of optimized molecule pairs. In this study, we present a novel molecular optimization paradigm, Graph Polish. In this paradigm, with the guidance of the source and target molecule pairs of the desired properties, a heuristic optimization solution can be derived: given an input molecule, we first predict which atom can be viewed as the optimization center, and then the nearby regions are optimized around this center. We then propose an effective and efficient learning framework, Teacher and Student polish, to capture the dependencies in the optimization steps. A teacher component automatically identifies and annotates the optimization centers and the preservation, removal, and addition of some parts of the molecules; a student component learns these knowledges and applies them to a new molecule. The proposed paradigm can offer an intuitive interpretation for the molecular optimization result. Experiments with multiple optimization tasks are conducted on several benchmark datasets. The proposed approach achieves a significant advantage over the six state-ofthe-art baseline methods. Also, extensive studies are conducted to validate the effectiveness, explainability, and time savings of the novel optimization paradigm.

show abstract

“…The first term on right hand side of eq(1) measures how accurate is the generator, the second term denotes the divergence loss (KL divergence being a popular choice) that measures how closely the encoded latent variables match a unit Gaussian and λ is the scaling parameter [8]. In GANs, this divergence term is replaced by an adversarial network which tries to discriminate between original and generated samples [13], [26], [27], [28].…”

Section: A Backgroundmentioning

confidence: 99%

Improving Generative Modelling in VAEs Using Multimodal Prior

Abrol

Sharma

Patra

2021

IEEE Trans. Multimedia

View full text Add to dashboard Cite

In this paper we propose a conditional generative modelling (CGM) approach for unsupervised disentangled representation learning using variational autoencoder (VAE). CGM employs a multimodal/categorical conditional prior distribution in the latent space to learn global uncertainty in data by modelling the variations at local level. Thus, the proposed framework enforces the model to independently estimate the inherent patterns within each category, which improves the interpretability of the latent representations learned by the VAE model. The evidence lower bound objective for training the generative model is maximized using a mutual information criterion between the global latent categorical variable and the encoded inputs. Further, the approach has a built-in mechanism for bounding the information flow between the encoder and the decoder which addresses the problems of posterior collapse in conventional VAE models. Experiments on a variety of datasets demonstrate that our objective can learn disentangled representations and the proposed approach achieves competitive results on various task such as generative modelling, image classification and image denoising.

show abstract

Dual Adversarial Autoencoders for Clustering

Cited by 40 publications

References 22 publications

ECGAN: An Improved Conditional Generative Adversarial Network With Edge Detection to Augment Limited Training Data for the Classification of Remote Sensing Images With High Spatial Resolution

ECGAN: An Improved Conditional Generative Adversarial Network With Edge Detection to Augment Limited Training Data for the Classification of Remote Sensing Images With High Spatial Resolution

Graph Polish: A Novel Graph Generation Paradigm for Molecular Optimization

Improving Generative Modelling in VAEs Using Multimodal Prior

Contact Info

Product

Resources

About