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.

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 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.

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.

Age Progression using Generative Adversarial Networks

2020 ◽  
Author(s):  
Pallavi Madhukar ◽  
Rachana Chetan ◽  
Supriya Prasad ◽  
Mohamed Shayan ◽  
B. Niranjana Krupa
Keyword(s):  
Generative Adversarial Networks ◽  
Age Progression ◽  
Adversarial Networks

scholarly journals Deeply Learned Pose Invariant Image Analysis with Applications in 3D Face Recognition

2019 ◽  
Vol 2019 ◽  
pp. 1-21 ◽  
Author(s):  
Naeem Ratyal ◽  
Imtiaz Ahmad Taj ◽  
Muhammad Sajid ◽  
Anzar Mahmood ◽  
Sohail Razzaq ◽  
...  
Keyword(s):  
Face Recognition ◽  
Superior Performance ◽  
Support Vector ◽  
Complex Nature ◽  
Alignment Algorithm ◽  
3D Face Recognition ◽  
3D Face ◽  
Norm Minimization ◽  
Wide Range ◽  
The Face

Face recognition aims to establish the identity of a person based on facial characteristics and is a challenging problem due to complex nature of the facial manifold. A wide range of face recognition applications are based on classification techniques and a class label is assigned to the test image that belongs to the unknown class. In this paper, a pose invariant deeply learned multiview 3D face recognition approach is proposed and aims to address two problems: face alignment and face recognition through identification and verification setups. The proposed alignment algorithm is capable of handling frontal as well as profile face images. It employs a nose tip heuristic based pose learning approach to estimate acquisition pose of the face followed by coarse to fine nose tip alignment using L2 norm minimization. The whole face is then aligned through transformation using knowledge learned from nose tip alignment. Inspired by the intrinsic facial symmetry of the Left Half Face (LHF) and Right Half Face (RHF), Deeply learned (d) Multi-View Average Half Face (d-MVAHF) features are employed for face identification using deep convolutional neural network (dCNN). For face verification d-MVAHF-Support Vector Machine (d-MVAHF-SVM) approach is employed. The performance of the proposed methodology is demonstrated through extensive experiments performed on four databases: GavabDB, Bosphorus, UMB-DB, and FRGC v2.0. The results show that the proposed approach yields superior performance as compared to existing state-of-the-art methods.

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 Improving Juvenile Age Estimation Based on Facial Landmark Points and Gravity Moment

2020 ◽  
Vol 10 (18) ◽  
pp. 6227
Author(s):  
Ebenezer Nii Ayi Hammond ◽  
Shijie Zhou ◽  
Hongrong Cheng ◽  
Qihe Liu
Keyword(s):  
Age Estimation ◽  
Real Life ◽  
Research Network ◽  
Superior Performance ◽  
Detection Scheme ◽  
Facial Landmark ◽  
Juvenile Age ◽  
Facial Shape ◽  
The Face ◽  
Reference Matrix

Facial age estimation is of interest due to its potential to be applied in many real-life situations. However, recent age estimation efforts do not consider juveniles. Consequently, we introduce a juvenile age detection scheme called LaGMO, which focuses on the juvenile aging cues of facial shape and appearance. LaGMO is a combination of facial landmark points and Term Frequency Inverse Gravity Moment (TF-IGM). Inspired by the formation of words from morphemes, we obtained facial appearance features comprising facial shape and wrinkle texture and represented them as terms that described the age of the face. By leveraging the implicit ordinal relationship between the frequencies of the terms in the face, TF-IGM was used to compute the weights of the terms. From these weights, we built a matrix that corresponds to the possibilities of the face belonging to the age. Next, we reduced the reference matrix according to the juvenile age range (0–17 years) and avoided the exhaustive search through the entire training set. LaGMO detects the age by the projection of an unlabeled face image onto the reference matrix; the value of the projection depicts the higher probability of the image belonging to the age. With Mean Absolute Error (MAE) of 89% on the Face and Gesture Recognition Research Network (FG-NET) dataset, our proposal demonstrated superior performance in juvenile age estimation.

Generative Adversarial Networks With Synthetic Training Data for Enforcing Manufacturing Constraints on Topology Optimization

2020 ◽  
Author(s):  
Michael Greminger
Keyword(s):  
Topology Optimization ◽  
Vector Space ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Manufacturing Constraints ◽  
Cnc Milling ◽  
Manufacturing Method ◽  
Latent Vector ◽  
Adversarial Networks ◽  
Manufacturing Methods

Abstract Topology optimization is a powerful tool to generate mechanical designs that use minimal mass to achieve their function. However, the designs obtained using topology optimization are often not manufacturable using a given manufacturing process. There exist some modifications to the traditional topology optimization algorithm that are able to impose manufacturing constraints for a limited set of manufacturing methods. These approaches have the drawback that they are often based on heuristics to obtain the manufacturability constraint and thus cannot be applied generally to multiple manufacturing methods. In order to create a general approach to imposing manufacturing constraints on topology optimization, generative adversarial networks (GANs) are used. GANs have the capability to produce samples from a distribution defined by training data. In this work, the GAN is trained by generating synthetic 3D voxel training data that represent the distribution of designs that can be created by a particular manufacturing method. Once trained, the GAN forms a mapping from a latent vector space to the space of manufacturable designs. The topology optimization is then performed on the latent vector space ensuring that the design obtained is manufacturable. The effectiveness of this approach is demonstrated by training a GAN on designs intended to be manufacturable on a 3-axis computer numerically controlled (CNC) milling machine.

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.

Sign in / Sign up

Export Citation Format

Share Document