scholarly journals A Data-Centric Augmentation Approach for Disturbed Sensor Image Segmentation

2021 ◽  
Vol 7 (10) ◽  
pp. 206
Author(s):  
Andreas Roth ◽  
Konstantin Wüstefeld ◽  
Frank Weichert
Keyword(s):  
Deep Neural Networks ◽  
Generative Adversarial Networks ◽  
Image Artifacts ◽  
Generalization Capability ◽  
Detection Problem ◽  
Training Set ◽  
Time Consumption ◽  
Adversarial Networks ◽  
Direct Use ◽  
Additional Memory

Deep learning methods have become increasingly popular for optical sensor image analysis. They are adaptable to specific tasks and simultaneously demonstrate a high degree of generalization capability. However, applying deep neural networks to problems with low availability of labeled training data can lead to a model being incapable of generalizing to possible scenarios that may occur in test data, especially with the occurrence of dominant imaging artifacts. We propose a data-centric augmentation approach based on generative adversarial networks that overlays the existing labeled data with synthetic artifacts that are generated from data not present in the training set. This augmentation leads to a more robust generalization capability in semantic segmentation. Our method does not need any additional labeling and does not lead to additional memory or time consumption during inference. Further, we find it to be more effective than comparable approaches that are based on procedurally generated disturbances and the direct use of real disturbances. Building upon the improved segmentation results, we observe that our approach leads to improvements of 22% in the F1-score for an evaluated detection problem, which promises significant robustness towards future disturbances. In the context of sensor-based data analysis, the compensation of image artifacts is a challenge. When the structures of interest are not clearly visible in an image, algorithms that can cope with artifacts are crucial for obtaining the desired information. Thereby, the high variation of artifacts, the combination of different types of artifacts, and their similarity to signals of interest are specific issues that have to be considered in the analysis. Despite the high generalization capability of deep learning-based approaches, their recent success was driven by the availability of large amounts of labeled data. Therefore, the provision of comprehensive labeled image data with different characteristics of image artifacts is of importance. At the same time, applying deep neural networks to problems with low availability of labeled data remains a challenge. This work presents a data-centric augmentation approach based on generative adversarial networks that augments the existing labeled data with synthetic artifacts generated from data not present in the training set. In our experiments, this augmentation leads to a more robust generalization in segmentation. Our method does not need additional labeling and does not lead to additional memory or time consumption during inference. Further, we find it to be more effective than comparable augmentations based on procedurally generated artifacts and the direct use of real artifacts. Building upon the improved segmentation results, we observe that our approach leads to improvements of 22% in the F1-score for an evaluated detection problem. Having achieved these results with an example sensor, we expect increased robustness against artifacts in future applications.

scholarly journals Generalization of Deep Neural Networks for Imbalanced Fault Classification of Machinery Using Generative Adversarial Networks

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 111168-111180 ◽  
Author(s):  
Jinrui Wang ◽  
Shunming Li ◽  
Baokun Han ◽  
Zenghui An ◽  
Huaiqian Bao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Fault Classification ◽  
Generative Adversarial Networks ◽  
Adversarial Networks

scholarly journals Generating Adversarial Examples with Adversarial Networks

2018 ◽  
Author(s):  
Chaowei Xiao ◽  
Bo Li ◽  
Jun-yan Zhu ◽  
Warren He ◽  
Mingyan Liu ◽  
...  
Keyword(s):  
Deep Neural Networks ◽  
State Of The Art ◽  
Black Box ◽  
Generative Adversarial Networks ◽  
Perceptual Quality ◽  
Small Magnitude ◽  
Adversarial Networks ◽  
Original Target ◽  
Adversarial Examples ◽  
Adversarial Training

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mislead DNNs to produce adversary-selected results. Different attack strategies have been proposed to generate adversarial examples, but how to produce them with high perceptual quality and more efficiently requires more research efforts. In this paper, we propose AdvGAN to generate adversarial exam- ples with generative adversarial networks (GANs), which can learn and approximate the distribution of original instances. For AdvGAN, once the generator is trained, it can generate perturbations efficiently for any instance, so as to potentially accelerate adversarial training as defenses. We apply Adv- GAN in both semi-whitebox and black-box attack settings. In semi-whitebox attacks, there is no need to access the original target model after the generator is trained, in contrast to traditional white-box attacks. In black-box attacks, we dynamically train a distilled model for the black-box model and optimize the generator accordingly. Adversarial examples generated by AdvGAN on different target models have high attack success rate under state-of-the-art defenses compared to other attacks. Our attack has placed the first with 92.76% accuracy on a public MNIST black-box attack challenge.

scholarly journals Generative Adversarial Positive-Unlabelled Learning

2018 ◽  
Author(s):  
Ming Hou ◽  
Brahim Chaib-draa ◽  
Chao Li ◽  
Qibin Zhao
Keyword(s):  
Neural Networks ◽  
Theoretical Analysis ◽  
Supervised Classification ◽  
Deep Neural Networks ◽  
Generative Adversarial Networks ◽  
Discriminative Learning ◽  
Decision Boundary ◽  
Negative Data ◽  
New Paradigm ◽  
Adversarial Networks

 In this work, we consider the task of classifying binary positive-unlabeled (PU) data. The existing discriminative learning based PU models attempt to seek an optimal reweighting strategy for U data, so that a decent decision boundary can be found. However, given limited P data, the conventional PU models tend to suffer from overfitting when adapted to very flexible deep neural networks. In contrast, we are the first to innovate a totally new paradigm to attack the binary PU task, from perspective of generative learning by leveraging the powerful generative adversarial networks (GAN). Our generative positive-unlabeled (GenPU) framework incorporates an array of discriminators and generators that are endowed with different roles in simultaneously producing positive and negative realistic samples. We provide theoretical analysis to justify that, at equilibrium, GenPU is capable of recovering both positive and negative data distributions. Moreover, we show GenPU is generalizable and closely related to the semi-supervised classification. Given rather limited P data, experiments on both synthetic and real-world dataset demonstrate the effectiveness of our proposed framework. With infinite realistic and diverse sample streams generated from GenPU, a very flexible classifier can then be trained using deep neural networks.

scholarly journals P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection

2020 ◽  
Author(s):  
Zhiwei Zhang ◽  
Shifeng Chen ◽  
Lei Sun
Keyword(s):  
Deep Neural Networks ◽  
Novelty Detection ◽  
Single Step ◽  
Basic Knowledge ◽  
Generative Adversarial Networks ◽  
Second Step ◽  
Adversarial Networks ◽  
Resource Limited ◽  
Trained Teacher ◽  
Knowledge Distillation

One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection and achieve state-of-the-art performance. However, deep neural networks are too over-parameterized to deploy on resource-limited devices. Therefore, Progressive Knowledge Distillation with GANs (P-KDGAN) is proposed to learn compact and fast novelty detection networks. The P-KDGAN is a novel attempt to connect two standard GANs by the designed distillation loss for transferring knowledge from the teacher to the student. The progressive learning of knowledge distillation is a two-step approach that continuously improves the performance of the student GAN and achieves better performance than single step methods. In the first step, the student GAN learns the basic knowledge totally from the teacher via guiding of the pre-trained teacher GAN with fixed weights. In the second step, joint fine-training is adopted for the knowledgeable teacher and student GANs to further improve the performance and stability. The experimental results on CIFAR-10, MNIST, and FMNIST show that our method improves the performance of the student GAN by 2.44%, 1.77%, and 1.73% when compressing the computation at ratios of 24.45:1, 311.11:1, and 700:1, respectively.

scholarly journals Disentangled Face Attribute Editing via Instance-Aware Latent Space Search

2021 ◽  
Author(s):  
Yuxuan Han ◽  
Jiaolong Yang ◽  
Ying Fu
Keyword(s):  
Optimal Control ◽  
State Of The Art ◽  
Attribute Level ◽  
Generative Adversarial Networks ◽  
Control Factor ◽  
Training Set ◽  
Wide Margin ◽  
Adversarial Networks ◽  
Latent Space ◽  
Model Complex

Recent works have shown that a rich set of semantic directions exist in the latent space of Generative Adversarial Networks (GANs), which enables various facial attribute editing applications. However, existing methods may suffer poor attribute variation disentanglement, leading to unwanted change of other attributes when altering the desired one. The semantic directions used by existing methods are at attribute level, which are difficult to model complex attribute correlations, especially in the presence of attribute distribution bias in GAN's training set. In this paper, we propose a novel framework (IALS) that performs Instance-Aware Latent-Space Search to find semantic directions for disentangled attribute editing. The instance information is injected by leveraging the supervision from a set of attribute classifiers evaluated on the input images. We further propose a Disentanglement-Transformation (DT) metric to quantify the attribute transformation and disentanglement efficacy and find the optimal control factor between attribute-level and instance-specific directions based on it. Experimental results on both GAN-generated and real-world images collectively show that our method outperforms state-of-the-art methods proposed recently by a wide margin. Code is available at https://github.com/yxuhan/IALS.

scholarly journals Generative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning

2019 ◽  
Vol 490 (4) ◽  
pp. 4985-4990 ◽  
Author(s):  
Michael J Smith ◽  
James E Geach
Keyword(s):  
Hubble Space Telescope ◽  
Synthetic Data ◽  
Generative Adversarial Networks ◽  
Training Set ◽  
Training Images ◽  
Adversarial Networks ◽  
Data Driven Approach ◽  
Astronomical Images ◽  
Deep Fields ◽  
High Level

ABSTRACT Generative adversarial networks (GANs) are a class of artificial neural network that can produce realistic, but artificial, images that resemble those in a training set. In typical GAN architectures these images are small, but a variant known as Spatial GANs (SGANs) can generate arbitrarily large images, provided training images exhibit some level of periodicity. Deep extragalactic imaging surveys meet this criteria due to the cosmological tenet of isotropy. Here we train an SGAN to generate images resembling the iconic Hubble Space Telescope eXtreme Deep Field (XDF). We show that the properties of ‘galaxies’ in generated images have a high level of fidelity with galaxies in the real XDF in terms of abundance, morphology, magnitude distributions, and colours. As a demonstration we have generated a 7.6-billion pixel ‘generative deep field’ spanning 1.45 deg. The technique can be generalized to any appropriate imaging training set, offering a new purely data-driven approach for producing realistic mock surveys and synthetic data at scale, in astrophysics and beyond.

scholarly journals Generative Adversarial Networks for Pre-training of Medical Image Segmentation Networks

2020 ◽  
Author(s):  
Kun Chen ◽  
Manning Wang ◽  
Zhijian Song
Keyword(s):  
Neural Networks ◽  
Image Segmentation ◽  
Medical Image ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Medical Image Segmentation ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Synthetic Images

Abstract Background: Deep neural networks have been widely used in medical image segmentation and have achieved state-of-the-art performance in many tasks. However, different from the segmentation of natural images or video frames, the manual segmentation of anatomical structures in medical images needs high expertise so the scale of labeled training data is very small, which is a major obstacle for the improvement of deep neural networks performance in medical image segmentation. Methods: In this paper, we proposed a new end-to-end generation-segmentation framework by integrating Generative Adversarial Networks (GAN) and a segmentation network and train them simultaneously. The novelty is that during the training of the GAN, the intermediate synthetic images generated by the generator of the GAN are used to pre-train the segmentation network. As the advances of the training of the GAN, the synthetic images evolve gradually from being very coarse to containing more realistic textures, and these images help train the segmentation network gradually. After the training of GAN, the segmentation network is then fine-tuned by training with the real labeled images. Results: We evaluated the proposed framework on four different datasets, including 2D cardiac dataset and lung dataset, 3D prostate dataset and liver dataset. Compared with original U-net and CE-Net, our framework can achieve better segmentation performance. Our framework also can get better segmentation results than U-net on small datasets. In addition, our framework is more effective than the usual data augmentation methods. Conclusions: The proposed framework can be used as a pre-train method of segmentation network, which helps to get a better segmentation result. Our method can solve the shortcomings of current data augmentation methods to some extent.

Sign in / Sign up

Export Citation Format

Share Document