scholarly journals ClusterGAN: Latent Space Clustering in Generative Adversarial Networks

2019 ◽  
Vol 33 ◽  
pp. 4610-4617 ◽  
Author(s):  
Sudipto Mukherjee ◽  
Himanshu Asnani ◽  
Eugene Lin ◽  
Sreeram Kannan
Keyword(s):  
Unsupervised Learning ◽  
Latent Variables ◽  
Cluster Structure ◽  
Superior Performance ◽  
Generative Adversarial Networks ◽  
Back Projection ◽  
Learning Problem ◽  
Adversarial Networks ◽  
Learning Tasks ◽  
Latent Space

Generative Adversarial networks (GANs) have obtained remarkable success in many unsupervised learning tasks and unarguably, clustering is an important unsupervised learning problem. While one can potentially exploit the latent-space back-projection in GANs to cluster, we demonstrate that the cluster structure is not retained in the GAN latent space. In this paper, we propose ClusterGAN as a new mechanism for clustering using GANs. By sampling latent variables from a mixture of one-hot encoded variables and continuous latent variables, coupled with an inverse network (which projects the data to the latent space) trained jointly with a clustering specific loss, we are able to achieve clustering in the latent space. Our results show a remarkable phenomenon that GANs can preserve latent space interpolation across categories, even though the discriminator is never exposed to such vectors. We compare our results with various clustering baselines and demonstrate superior performance on both synthetic and real datasets.

scholarly journals Parallel Image Completion with Edge and Color Map

2019 ◽  
Vol 9 (18) ◽  
pp. 3856 ◽  
Author(s):  
Dan Zhao ◽  
Baolong Guo ◽  
Yunyi Yan
Keyword(s):  
Superior Performance ◽  
Generative Adversarial Networks ◽  
Image Completion ◽  
Significant Progress ◽  
Color Information ◽  
Parallel Edge ◽  
Adversarial Networks ◽  
Parallel Image ◽  
Latent Space ◽  
Image Edge

Over the last few years, image completion has made significant progress due to the generative adversarial networks (GANs) that are able to synthesize photorealistic contents. However, one of the main obstacles faced by many existing methods is that they often create blurry textures or distorted structures that are inconsistent with surrounding regions. The main reason is the ineffectiveness of disentangling style latent space implicitly from images. To address this problem, we develop a novel image completion framework called PIC-EC: parallel image completion networks with edge and color maps, which explicitly provides image edge and color information as the prior knowledge for image completion. The PIC-EC framework consists of the parallel edge and color generators followed by an image completion network. Specifically, the parallel paths generate edge and color maps for the missing region at the same time, and then the image completion network fills the missing region with fine details using the generated edge and color information as the priors. The proposed method was evaluated over CelebA-HQ and Paris StreetView datasets. Experimental results demonstrate that PIC-EC achieves superior performance on challenging cases with complex compositions and outperforms existing methods on evaluations of realism and accuracy, both quantitatively and qualitatively.

An anomaly detection method based on double encoder–decoder generative adversarial networks

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hui Liu ◽  
Tinglong Tang ◽  
Jake Luo ◽  
Meng Zhao ◽  
Baole Zheng ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Latent Variables ◽  
Dimensional Space ◽  
Superior Performance ◽  
Generative Adversarial Networks ◽  
Training Process ◽  
Content Type ◽  
Detection Model ◽  
Adversarial Networks ◽  
Low Dimensional

Purpose This study aims to address the challenge of training a detection model for the robot to detect the abnormal samples in the industrial environment, while abnormal patterns are very rare under this condition. Design/methodology/approach The authors propose a new model with double encoder–decoder (DED) generative adversarial networks to detect anomalies when the model is trained without any abnormal patterns. The DED approach is used to map high-dimensional input images to a low-dimensional space, through which the latent variables are obtained. Minimizing the change in the latent variables during the training process helps the model learn the data distribution. Anomaly detection is achieved by calculating the distance between two low-dimensional vectors obtained from two encoders. Findings The proposed method has better accuracy and F1 score when compared with traditional anomaly detection models. Originality/value A new architecture with a DED pipeline is designed to capture the distribution of images in the training process so that anomalous samples are accurately identified. A new weight function is introduced to control the proportion of losses in the encoding reconstruction and adversarial phases to achieve better results. An anomaly detection model is proposed to achieve superior performance against prior state-of-the-art approaches.

scholarly journals A deep learning approach to capture the essence of Candida albicans morphologies

2021 ◽  
Author(s):  
Van Bettauer ◽  
Anna CBP Costa ◽  
Raha Parvizi Omran ◽  
Samira Massahi ◽  
Eftyhios Kirbizakis ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Strategy ◽  
Developmental Trajectories ◽  
Generative Adversarial Networks ◽  
Learning Approach ◽  
Adversarial Networks ◽  
Latent Space ◽  
Contrast Microscopy ◽  
Opportunistic Human Pathogen ◽  
Community Meeting

We present deep learning-based approaches for exploring the complex array of morphologies exhibited by the opportunistic human pathogen C. albicans. Our system entitled Candescence automatically detects C. albicans cells from Differential Image Contrast microscopy, and labels each detected cell with one of nine vegetative, mating-competent or filamentous morphologies. The software is based upon a fully convolutional one-stage object detector and exploits a novel cumulative curriculum-based learning strategy that stratifies our images by difficulty from simple vegetative forms to more complex filamentous architectures. Candescence achieves very good performance on this difficult learning set which has substantial intermixing between the predicted classes. To capture the essence of each C. albicans morphology, we develop models using generative adversarial networks and identify subcomponents of the latent space which control technical variables, developmental trajectories or morphological switches. We envision Candescence as a community meeting point for quantitative explorations of C. albicans morphology.

scholarly journals RoCGAN: Robust Conditional GAN

2020 ◽  
Vol 128 (10-11) ◽  
pp. 2665-2683 ◽  
Author(s):  
Grigorios G. Chrysos ◽  
Jean Kossaifi ◽  
Stefanos Zafeiriou
Keyword(s):  
Large Scale ◽  
Real Data ◽  
Superior Performance ◽  
Target Space ◽  
Generative Adversarial Networks ◽  
Natural Scenes ◽  
Adversarial Networks ◽  
Target Manifold ◽  
The Face ◽  
Intense Noise

Abstract Conditional image generation lies at the heart of computer vision and conditional generative adversarial networks (cGAN) have recently become the method of choice for this task, owing to their superior performance. The focus so far has largely been on performance improvement, with little effort in making cGANs more robust to noise. However, the regression (of the generator) might lead to arbitrarily large errors in the output, which makes cGANs unreliable for real-world applications. In this work, we introduce a novel conditional GAN model, called RoCGAN, which leverages structure in the target space of the model to address the issue. Specifically, we augment the generator with an unsupervised pathway, which promotes the outputs of the generator to span the target manifold, even in the presence of intense noise. We prove that RoCGAN share similar theoretical properties as GAN and establish with both synthetic and real data the merits of our model. We perform a thorough experimental validation on large scale datasets for natural scenes and faces and observe that our model outperforms existing cGAN architectures by a large margin. We also empirically demonstrate the performance of our approach in the face of two types of noise (adversarial and Bernoulli).

scholarly journals Collective dynamics of repeated inference in variational autoencoder rapidly find cluster structure

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Yoshihiro Nagano ◽  
Ryo Karakida ◽  
Masato Okada
Keyword(s):  
Activity Pattern ◽  
Latent Variables ◽  
Cluster Structure ◽  
Generative Models ◽  
Cluster Center ◽  
Specific Data ◽  
Global Cluster ◽  
Latent Space ◽  
Variational Autoencoder ◽  
Low Dimensional

Abstract Deep neural networks are good at extracting low-dimensional subspaces (latent spaces) that represent the essential features inside a high-dimensional dataset. Deep generative models represented by variational autoencoders (VAEs) can generate and infer high-quality datasets, such as images. In particular, VAEs can eliminate the noise contained in an image by repeating the mapping between latent and data space. To clarify the mechanism of such denoising, we numerically analyzed how the activity pattern of trained networks changes in the latent space during inference. We considered the time development of the activity pattern for specific data as one trajectory in the latent space and investigated the collective behavior of these inference trajectories for many data. Our study revealed that when a cluster structure exists in the dataset, the trajectory rapidly approaches the center of the cluster. This behavior was qualitatively consistent with the concept retrieval reported in associative memory models. Additionally, the larger the noise contained in the data, the closer the trajectory was to a more global cluster. It was demonstrated that by increasing the number of the latent variables, the trend of the approach a cluster center can be enhanced, and the generalization ability of the VAE can be improved.

Topology Design With Conditional Generative Adversarial Networks

2019 ◽  
Author(s):  
Conner Sharpe ◽  
Carolyn Conner Seepersad
Keyword(s):  
Engineering Design ◽  
Latent Variables ◽  
Computational Design ◽  
Optimization Techniques ◽  
Topology Design ◽  
Generative Adversarial Networks ◽  
Design Parameters ◽  
Full Potential ◽  
Adversarial Networks ◽  
Analytical Sensitivities

Abstract Deep convolutional neural networks have gained significant traction as effective approaches for developing detailed but compact representations of complex structured data. Generative networks in particular have become popular for their ability to mimic data distributions and allow further exploration of them. This attribute can be utilized in engineering design domains, in which the data structures of finite element meshes for analyzing potential designs are well suited to the deep convolutional network approaches that are being developed at a rapid pace in the field of image processing. This paper explores the use of conditional generative adversarial networks (cGANs) as a means of generating a compact latent representation of structures resulting from classical topology optimization techniques. The constraints and contextual factors of a design problem, such as mass fraction, material type, and load location, can then be specified as input conditions to generate potential topologies in a directed fashion. The trained network can be used to aid concept generation, such that engineers can explore a variety of designs relevant to the problem at hand with ease. The latent variables of the generator can also be used as design parameters, and the low dimensionality enables tractable computational design without analytical sensitivities. This paper demonstrates these capabilities and discusses avenues for further developments that would enable the engineering design community to further leverage generative machine learning techniques to their full potential.

scholarly journals AgeFlow: Conditional Age Progression and Regression with Normalizing Flows

2021 ◽  
Author(s):  
Zhizhong Huang ◽  
Shouzhen Chen ◽  
Junping Zhang ◽  
Hongming Shan
Keyword(s):  
Superior Performance ◽  
Generative Adversarial Networks ◽  
Traditional Use ◽  
Image Domain ◽  
Age Progression ◽  
Latent Vector ◽  
Latent Space ◽  
The Face ◽  
Knowledge Distillation ◽  
Facial Attributes

Age progression and regression aim to synthesize photorealistic appearance of a given face image with aging and rejuvenation effects, respectively. Existing generative adversarial networks (GANs) based methods suffer from the following three major issues: 1) unstable training introducing strong ghost artifacts in the generated faces, 2) unpaired training leading to unexpected changes in facial attributes such as genders and races, and 3) non-bijective age mappings increasing the uncertainty in the face transformation. To overcome these issues, this paper proposes a novel framework, termed AgeFlow, to integrate the advantages of both flow-based models and GANs. The proposed AgeFlow contains three parts: an encoder that maps a given face to a latent space through an invertible neural network, a novel invertible conditional translation module (ICTM) that translates the source latent vector to target one, and a decoder that reconstructs the generated face from the target latent vector using the same encoder network; all parts are invertible achieving bijective age mappings. The novelties of ICTM are two-fold. First, we propose an attribute-aware knowledge distillation to learn the manipulation direction of age progression while keeping other unrelated attributes unchanged, alleviating unexpected changes in facial attributes. Second, we propose to use GANs in the latent space to ensure the learned latent vector indistinguishable from the real ones, which is much easier than traditional use of GANs in the image domain. Experimental results demonstrate superior performance over existing GANs-based methods on two benchmarked datasets. The source code is available at https://github.com/Hzzone/AgeFlow.

Synthesizing Designs With Interpart Dependencies Using Hierarchical Generative Adversarial Networks

2019 ◽  
Vol 141 (11) ◽  
Author(s):  
Wei Chen ◽  
Mark Fuge
Keyword(s):  
Constraint Satisfaction ◽  
Real World ◽  
Generative Models ◽  
Dependency Graph ◽  
Generative Adversarial Networks ◽  
Engineering Systems ◽  
Adversarial Networks ◽  
Latent Space ◽  
Branching Factor ◽  
Low Dimensional

Abstract Real-world designs usually consist of parts with interpart dependencies, i.e., the geometry of one part is dependent on one or multiple other parts. We can represent such dependency in a part dependency graph. This paper presents a method for synthesizing these types of hierarchical designs using generative models learned from examples. It decomposes the problem of synthesizing the whole design into synthesizing each part separately but keeping the interpart dependencies satisfied. Specifically, this method constructs multiple generative models, the interaction of which is based on the part dependency graph. We then use the trained generative models to synthesize or explore each part design separately via a low-dimensional latent representation, conditioned on the corresponding parent part(s). We verify our model on multiple design examples with different interpart dependencies. We evaluate our model by analyzing the constraint satisfaction performance, the synthesis quality, the latent space quality, and the effects of part dependency depth and branching factor. This paper’s techniques for capturing dependencies among parts lay the foundation for learned generative models to extend to more realistic engineering systems where such relationships are widespread.

Sign in / Sign up

Export Citation Format

Share Document