scholarly journals Learning to Transfer: Unsupervised Domain Translation via Meta-Learning

2020 ◽  
Vol 34 (07) ◽  
pp. 11507-11514
Author(s):  
Jianxin Lin ◽  
Yijun Wang ◽  
Zhibo Chen ◽  
Tianyu He

Unsupervised domain translation has recently achieved impressive performance with Generative Adversarial Network (GAN) and sufficient (unpaired) training data. However, existing domain translation frameworks form in a disposable way where the learning experiences are ignored and the obtained model cannot be adapted to a new coming domain. In this work, we take on unsupervised domain translation problems from a meta-learning perspective. We propose a model called Meta-Translation GAN (MT-GAN) to find good initialization of translation models. In the meta-training procedure, MT-GAN is explicitly trained with a primary translation task and a synthesized dual translation task. A cycle-consistency meta-optimization objective is designed to ensure the generalization ability. We demonstrate effectiveness of our model on ten diverse two-domain translation tasks and multiple face identity translation tasks. We show that our proposed approach significantly outperforms the existing domain translation methods when each domain contains no more than ten training samples.

2020 ◽  
Vol 27 (2) ◽  
pp. 486-493 ◽  
Author(s):  
Xiaogang Yang ◽  
Maik Kahnt ◽  
Dennis Brückner ◽  
Andreas Schropp ◽  
Yakub Fam ◽  
...  

This paper presents a deep learning algorithm for tomographic reconstruction (GANrec). The algorithm uses a generative adversarial network (GAN) to solve the inverse of the Radon transform directly. It works for independent sinograms without additional training steps. The GAN has been developed to fit the input sinogram with the model sinogram generated from the predicted reconstruction. Good quality reconstructions can be obtained during the minimization of the fitting errors. The reconstruction is a self-training procedure based on the physics model, instead of on training data. The algorithm showed significant improvements in the reconstruction accuracy, especially for missing-wedge tomography acquired at less than 180° rotational range. It was also validated by reconstructing a missing-wedge X-ray ptychographic tomography (PXCT) data set of a macroporous zeolite particle, for which only 51 projections over 70° could be collected. The GANrec recovered the 3D pore structure with reasonable quality for further analysis. This reconstruction concept can work universally for most of the ill-posed inverse problems if the forward model is well defined, such as phase retrieval of in-line phase-contrast imaging.


2021 ◽  
Vol 2021 (2) ◽  
pp. 305-322
Author(s):  
Se Eun Oh ◽  
Nate Mathews ◽  
Mohammad Saidur Rahman ◽  
Matthew Wright ◽  
Nicholas Hopper

Abstract We introduce Generative Adversarial Networks for Data-Limited Fingerprinting (GANDaLF), a new deep-learning-based technique to perform Website Fingerprinting (WF) on Tor traffic. In contrast to most earlier work on deep-learning for WF, GANDaLF is intended to work with few training samples, and achieves this goal through the use of a Generative Adversarial Network to generate a large set of “fake” data that helps to train a deep neural network in distinguishing between classes of actual training data. We evaluate GANDaLF in low-data scenarios including as few as 10 training instances per site, and in multiple settings, including fingerprinting of website index pages and fingerprinting of non-index pages within a site. GANDaLF achieves closed-world accuracy of 87% with just 20 instances per site (and 100 sites) in standard WF settings. In particular, GANDaLF can outperform Var-CNN and Triplet Fingerprinting (TF) across all settings in subpage fingerprinting. For example, GANDaLF outperforms TF by a 29% margin and Var-CNN by 38% for training sets using 20 instances per site.


2020 ◽  
Vol 2020 (2) ◽  
pp. 17-23
Author(s):  
Vladislav Laptev ◽  
Vyacheslav Danilov ◽  
Olga Gerget

The paper considers the development of a Generative Adversarial Network (GAN) for the synthesis of new medical data. The developed GAN consists of two models trained simultaneously: a generative model (G - Generator), estimating the distribution of data, and a discriminating model (D - Discriminator), which estimates the probability that the sample is obtained from the training data, and not from generator G. To create G, we used own neural network architecture based on convolutional layers using experimental functions of Tensor Flow Addons. To create discriminator D, we used a Transfer Learning (TL) approach. The training procedure is to maximize the likelihood that discriminator D will make a mistake. Experiments show that the proposed GAN architecture completely copes with the task of synthesizing of new medical data.


Author(s):  
Annapoorani Gopal ◽  
Lathaselvi Gandhimaruthian ◽  
Javid Ali

The Deep Neural Networks have gained prominence in the biomedical domain, becoming the most commonly used networks after machine learning technology. Mammograms can be used to detect breast cancers with high precision with the help of Convolutional Neural Network (CNN) which is deep learning technology. An exhaustive labeled data is required to train the CNN from scratch. This can be overcome by deploying Generative Adversarial Network (GAN) which comparatively needs lesser training data during a mammogram screening. In the proposed study, the application of GANs in estimating breast density, high-resolution mammogram synthesis for clustered microcalcification analysis, effective segmentation of breast tumor, analysis of the shape of breast tumor, extraction of features and augmentation of the image during mammogram classification have been extensively reviewed.


Author(s):  
Xinyi Li ◽  
Liqiong Chang ◽  
Fangfang Song ◽  
Ju Wang ◽  
Xiaojiang Chen ◽  
...  

This paper focuses on a fundamental question in Wi-Fi-based gesture recognition: "Can we use the knowledge learned from some users to perform gesture recognition for others?". This problem is also known as cross-target recognition. It arises in many practical deployments of Wi-Fi-based gesture recognition where it is prohibitively expensive to collect training data from every single user. We present CrossGR, a low-cost cross-target gesture recognition system. As a departure from existing approaches, CrossGR does not require prior knowledge (such as who is currently performing a gesture) of the target user. Instead, CrossGR employs a deep neural network to extract user-agnostic but gesture-related Wi-Fi signal characteristics to perform gesture recognition. To provide sufficient training data to build an effective deep learning model, CrossGR employs a generative adversarial network to automatically generate many synthetic training data from a small set of real-world examples collected from a small number of users. Such a strategy allows CrossGR to minimize the user involvement and the associated cost in collecting training examples for building an accurate gesture recognition system. We evaluate CrossGR by applying it to perform gesture recognition across 10 users and 15 gestures. Experimental results show that CrossGR achieves an accuracy of over 82.6% (up to 99.75%). We demonstrate that CrossGR delivers comparable recognition accuracy, but uses an order of magnitude less training samples collected from the end-users when compared to state-of-the-art recognition systems.


Author(s):  
Huilin Zhou ◽  
Huimin Zheng ◽  
Qiegen Liu ◽  
Jian Liu ◽  
Yuhao Wang

Abstract Electromagnetic inverse-scattering problems (ISPs) are concerned with determining the properties of an unknown object using measured scattered fields. ISPs are often highly nonlinear, causing the problem to be very difficult to address. In addition, the reconstruction images of different optimization methods are distorted which leads to inaccurate reconstruction results. To alleviate these issues, we propose a new linear model solution of generative adversarial network-based (LM-GAN) inspired by generative adversarial networks (GAN). Two sub-networks are trained alternately in the adversarial framework. A linear deep iterative network as a generative network captures the spatial distribution of the data, and a discriminative network estimates the probability of a sample from the training data. Numerical results validate that LM-GAN has admirable fidelity and accuracy when reconstructing complex scatterers.


2021 ◽  
Vol 263 (2) ◽  
pp. 4558-4564
Author(s):  
Minghong Zhang ◽  
Xinwei Luo

Underwater acoustic target recognition is an important aspect of underwater acoustic research. In recent years, machine learning has been developed continuously, which is widely and effectively applied in underwater acoustic target recognition. In order to acquire good recognition results and reduce the problem of overfitting, Adequate data sets are essential. However, underwater acoustic samples are relatively rare, which has a certain impact on recognition accuracy. In this paper, in addition of the traditional audio data augmentation method, a new method of data augmentation using generative adversarial network is proposed, which uses generator and discriminator to learn the characteristics of underwater acoustic samples, so as to generate reliable underwater acoustic signals to expand the training data set. The expanded data set is input into the deep neural network, and the transfer learning method is applied to further reduce the impact caused by small samples by fixing part of the pre-trained parameters. The experimental results show that the recognition result of this method is better than the general underwater acoustic recognition method, and the effectiveness of this method is verified.


Author(s):  
S. M. Tilon ◽  
F. Nex ◽  
D. Duarte ◽  
N. Kerle ◽  
G. Vosselman

Abstract. Degradation and damage detection provides essential information to maintenance workers in routine monitoring and to first responders in post-disaster scenarios. Despite advance in Earth Observation (EO), image analysis and deep learning techniques, the quality and quantity of training data for deep learning is still limited. As a result, no robust method has been found yet that can transfer and generalize well over a variety of geographic locations and typologies of damages. Since damages can be seen as anomalies, occurring sparingly over time and space, we propose to use an anomaly detecting Generative Adversarial Network (GAN) to detect damages. The main advantages of using GANs are that only healthy unannotated images are needed, and that a variety of damages, including the never before seen damage, can be detected. In this study we aimed to investigate 1) the ability of anomaly detecting GANs to detect degradation (potholes and cracks) in asphalt road infrastructures using Mobile Mapper imagery and building damage (collapsed buildings, rubble piles) using post-disaster aerial imagery, and 2) the sensitivity of this method against various types of pre-processing. Our results show that we can detect damages in urban scenes at satisfying levels but not on asphalt roads. Future work will investigate how to further classify the found damages and how to improve damage detection for asphalt roads.


Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2919 ◽  
Author(s):  
Wangyong He ◽  
Zhongzhao Xie ◽  
Yongbo Li ◽  
Xinmei Wang ◽  
Wendi Cai

Hand pose estimation is a critical technology of computer vision and human-computer interaction. Deep-learning methods require a considerable amount of tagged data. Accordingly, numerous labeled training data are required. This paper aims to generate depth hand images. Given a ground-truth 3D hand pose, the developed method can generate depth hand images. To be specific, a ground truth can be 3D hand poses with the hand structure contained, while the synthesized image has an identical size to that of the training image and a similar visual appearance to the training set. The developed method, inspired by the progress in the generative adversarial network (GAN) and image-style transfer, helps model the latent statistical relationship between the ground-truth hand pose and the corresponding depth hand image. The images synthesized using the developed method are demonstrated to be feasible for enhancing performance. On public hand pose datasets (NYU, MSRA, ICVL), comprehensive experiments prove that the developed method outperforms the existing works.


Sign in / Sign up

Export Citation Format

Share Document