scholarly journals Generative Enhancement of 3D Image Classifiers

2020 ◽  
Vol 10 (21) ◽  
pp. 7433
Author(s):  
Michal Varga ◽  
Ján Jadlovský ◽  
Slávka Jadlovská
Keyword(s):  
Neural Networks ◽  
Knowledge Sharing ◽  
Classification Accuracy ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
3D Image ◽  
Accuracy Improvement ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Generative Modeling

In this paper, we propose a methodology for generative enhancement of existing 3D image classifiers. This methodology is based on combining the advantages of both non-generative classifiers and generative modeling. Its purpose is to streamline the synthesis of novel deep neural networks by embedding existing compatible classifiers into a generative network architecture. A demonstration of this process and evaluation of its effectiveness is performed using a 3D convolutional classifier and its generative equivalent—a 3D conditional generative adversarial network classifier. The results of the experiments show that the generative classifier delivers higher performance, gaining a relative classification accuracy improvement of 7.43%. An increase of accuracy is also observed when comparing it to a plain convolutional classifier that was trained on a dataset augmented with samples created by the trained generator. This suggests a desirable knowledge sharing mechanism exists within the hybrid discriminator-classifier network.

scholarly journals Generative Enhancement of 3D Image Classifiers

2020 ◽  
Author(s):  
Michal Varga ◽  
Ján Jadlovský ◽  
Slávka Jadlovská
Keyword(s):  
Knowledge Sharing ◽  
Classification Accuracy ◽  
Network Architecture ◽  
Classification Performance ◽  
Generative Model ◽  
3D Image ◽  
Accuracy Improvement ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Generative Modeling

Abstract In this paper, we propose a methodology for generative enhancement of existing 3D image classifiers. This methodology is based on combining the strengths of both non-generative classifiers and generative modeling. Its purpose is to streamline the creation of new classifiers by embedding existing compatible classifiers in a generative network architecture. The demonstration of this process and evaluation of its effects is performed using a 3D convolutional classifier and its generative equivalent - a conditional generative adversarial network classifier. The results show that the generative model achieves greater classification performance, gaining a relative classification accuracy improvement of 7.43%. Improvement of accuracy is also present when compared to a plain convolutional classifier trained on a dataset augmented with examples produced by a trained generator. This suggests there is a desirable knowledge sharing within the hybrid discriminator-classifier network.

scholarly journals Classification Accuracy Improvement for Small-Size Citrus Pests and Diseases Using Bridge Connections in Deep Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4992
Author(s):  
Shuli Xing ◽  
Malrey Lee
Keyword(s):  
Neural Networks ◽  
Classification Accuracy ◽  
Deep Neural Networks ◽  
Citrus Fruit ◽  
Target Object ◽  
Accuracy Improvement ◽  
Pests And Diseases ◽  
The Rich ◽  
New Feature ◽  
Bridge Connections

Due to the rich vitamin content in citrus fruit, citrus is an important crop around the world. However, the yield of these citrus crops is often reduced due to the damage of various pests and diseases. In order to mitigate these problems, several convolutional neural networks were applied to detect them. It is of note that the performance of these selected models degraded as the size of the target object in the image decreased. To adapt to scale changes, a new feature reuse method named bridge connection was developed. With the help of bridge connections, the accuracy of baseline networks was improved at little additional computation cost. The proposed BridgeNet-19 achieved the highest classification accuracy (95.47%), followed by the pre-trained VGG-19 (95.01%) and VGG-19 with bridge connections (94.73%). The use of bridge connections also strengthens the flexibility of sensors for image acquisition. It is unnecessary to pay more attention to adjusting the distance between a camera and pests and diseases.

scholarly journals Video Super-Resolution Based on Generative Adversarial Network and Edge Enhancement

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 459
Author(s):  
Jialu Wang ◽  
Guowei Teng ◽  
Ping An
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Visual Experience ◽  
Super Resolution ◽  
Ground Truth ◽  
Intermediate Result ◽  
Edge Enhancement ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Sr Reconstruction

With the help of deep neural networks, video super-resolution (VSR) has made a huge breakthrough. However, these deep learning-based methods are rarely used in specific situations. In addition, training sets may not be suitable because many methods only assume that under ideal circumstances, low-resolution (LR) datasets are downgraded from high-resolution (HR) datasets in a fixed manner. In this paper, we proposed a model based on Generative Adversarial Network (GAN) and edge enhancement to perform super-resolution (SR) reconstruction for LR and blur videos, such as closed-circuit television (CCTV). The adversarial loss allows discriminators to be trained to distinguish between SR frames and ground truth (GT) frames, which is helpful to produce realistic and highly detailed results. The edge enhancement function uses the Laplacian edge module to perform edge enhancement on the intermediate result, which helps further improve the final results. In addition, we add the perceptual loss to the loss function to obtain a higher visual experience. At the same time, we also tried training network on different datasets. A large number of experiments show that our method has advantages in the Vid4 dataset and other LR videos.

scholarly journals Generative Adversarial Phonology: Modeling unsupervised allophonic learning with neural networks

2019 ◽  
Author(s):  
Gasper Begus
Keyword(s):  
Neural Networks ◽  
Latent Variables ◽  
Network Architecture ◽  
Speech Disorders ◽  
Levels Of Abstraction ◽  
Generative Adversarial Network ◽  
Internal Representations ◽  
Adversarial Network ◽  
Training Interval ◽  
Speech Data

Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a dependency between random space and generated speech data in the Generative Adversarial Network architecture and proposes a methodology to uncover the network's internal representations that correspond to phonetic and phonological properties. The Generative Adversarial architecture is uniquely appropriate for modeling phonetic and phonological learning because the network is trained on unannotated raw acoustic data and learning is unsupervised without any language-specific assumptions or pre-assumed levels of abstraction. A Generative Adversarial Network was trained on an allophonic distribution in English, in which voiceless stops surface as aspirated word-initially before stressed vowels, except if preceded by a sibilant [s]. The network successfully learns the allophonic alternation: the network's generated speech signal contains the conditional distribution of aspiration duration. The paper proposes a technique for establishing the network's internal representations that identifies latent variables that correspond to, for example, presence of [s] and its spectral properties. By manipulating these variables, we actively control the presence of [s] and its frication amplitude in the generated outputs. This suggests that the network learns to use latent variables as an approximation of phonetic and phonological representations. Crucially, we observe that the dependencies learned in training extend beyond the training interval, which allows for additional exploration of learning representations. The paper also discusses how the network's architecture and innovative outputs resemble and differ from linguistic behavior in language acquisition, speech disorders, and speech errors, and how well-understood dependencies in speech data can help us interpret how neural networks learn their representations.

scholarly journals Frontal Cortex Segmentation of Brain PET Imaging Using Deep Neural Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Qianyi Zhan ◽  
Yuanyuan Liu ◽  
Yuan Liu ◽  
Wei Hu
Keyword(s):  
Neural Networks ◽  
Frontal Cortex ◽  
Pet Imaging ◽  
Deep Neural Networks ◽  
Ground Truth ◽  
Generative Adversarial Network ◽  
Learning Framework ◽  
Adversarial Network ◽  
Brain Pet ◽  
Positron Emission

18F-FDG positron emission tomography (PET) imaging of brain glucose use and amyloid accumulation is a research criteria for Alzheimer's disease (AD) diagnosis. Several PET studies have shown widespread metabolic deficits in the frontal cortex for AD patients. Therefore, studying frontal cortex changes is of great importance for AD research. This paper aims to segment frontal cortex from brain PET imaging using deep neural networks. The learning framework called Frontal cortex Segmentation model of brain PET imaging (FSPET) is proposed to tackle this problem. It combines the anatomical prior to frontal cortex into the segmentation model, which is based on conditional generative adversarial network and convolutional auto-encoder. The FSPET method is evaluated on a dataset of 30 brain PET imaging with ground truth annotated by a radiologist. Results that outperform other baselines demonstrate the effectiveness of the FSPET framework.

scholarly journals Wave-Tracking in the Surf Zone Using Coastal Video Imagery with Deep Neural Networks

Atmosphere ◽  
2020 ◽  
Vol 11 (3) ◽  
pp. 304 ◽  
Author(s):  
Jinah Kim ◽  
Jaeil Kim ◽  
Taekyung Kim ◽  
Dong Huh ◽  
Sofia Caires
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Surf Zone ◽  
Background Information ◽  
Wave Crest ◽  
Video Enhancement ◽  
Generative Adversarial Network ◽  
Video Imagery ◽  
Adversarial Network ◽  
Spatio Temporal

In this paper, we propose a series of procedures for coastal wave-tracking using coastal video imagery with deep neural networks. It consists of three stages: video enhancement, hydrodynamic scene separation and wave-tracking. First, a generative adversarial network, trained using paired raindrop and clean videos, is applied to remove image distortions by raindrops and to restore background information of coastal waves. Next, a hydrodynamic scene of propagated wave information is separated from surrounding environmental information in the enhanced coastal video imagery using a deep autoencoder network. Finally, propagating waves are tracked by registering consecutive images in the quality-enhanced and scene-separated coastal video imagery using a spatial transformer network. The instantaneous wave speed of each individual wave crest and breaker in the video domain is successfully estimated through learning the behavior of transformed and propagated waves in the surf zone using deep neural networks. Since it enables the acquisition of spatio-temporal information of the surf zone though the characterization of wave breakers inclusively wave run-up, we expect that the proposed framework with the deep neural networks leads to improve understanding of nearshore wave dynamics.

scholarly journals Cryptospace Invertible Steganography with Conditional Generative Adversarial Networks

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Ching-Chun Chang
Keyword(s):  
Neural Networks ◽  
Intelligent Systems ◽  
Deep Neural Networks ◽  
Binary Classification ◽  
Classification Problem ◽  
Generative Adversarial Networks ◽  
Discrimination Function ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Bit Planes

Deep neural networks have become the foundation of many modern intelligent systems. Recently, the author has explored adversarial learning for invertible steganography (ALIS) and demonstrated the potential of deep neural networks to reinvigorate an obsolete invertible steganographic method. With the worldwide popularisation of the Internet of things and cloud computing, invertible steganography can be recognised as a favourable way of facilitating data management and authentication due to the ability to embed information without causing permanent distortion. In light of growing concerns over cybersecurity, it is important to take a step forwards to investigate invertible steganography for encrypted data. Indeed, the multidisciplinary research in invertible steganography and cryptospace computing has received considerable attention. In this paper, we extend previous work and address the problem of cryptospace invertible steganography with deep neural networks. Specifically, we revisit a seminal work on cryptospace invertible steganography in which the problem of message decoding and image recovery is viewed as a type of binary classification. We formulate a general expression encompassing spatial, spectral, and structural analyses towards this particular classification problem and propose a novel discrimination function based on a recurrent conditional generative adversarial network (RCGAN) which predicts bit-planes with stacked neural networks in a top-down manner. Experimental results evaluate the performance of various discrimination functions and validate the superiority of neural-network-aided discrimination function in terms of classification accuracy.

scholarly journals Multiterminal Pathfinding in Practical VLSI Systems with Deep Neural Networks

2022 ◽  
Author(s):  
Dmitry Utyamishev ◽  
Inna Partin-Vaisband
Keyword(s):  
Neural Networks ◽  
High Throughput ◽  
Deep Neural Networks ◽  
Task Complexity ◽  
State Of The Art ◽  
Synthetic Dataset ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Deep Image ◽  
Magnitude Improvement

Abstract A multiterminal obstacle-avoiding pathfinding approach is proposed. The approach is inspired by deep image learning. The key idea is based on training a conditional generative adversarial network (cGAN) to interpret a pathfinding task as a graphical bitmap and consequently map a pathfinding task onto a pathfinding solution represented by another bitmap. To enable the proposed cGAN pathfinding, a methodology for generating synthetic dataset is also proposed. The cGAN model is implemented in Python/Keras, trained on synthetically generated data, evaluated on practical VLSI benchmarks, and compared with state-of-the-art. Due to effective parallelization on GPU hardware, the proposed approach yields a state-of-the-art like wirelength and a better runtime and throughput for moderately complex pathfinding tasks. However, the runtime and throughput with the proposed approach remain constant with an increasing task complexity, promising orders of magnitude improvement over state-of-the-art in complex pathfinding tasks. The cGAN pathfinder can be exploited in numerous high throughput applications, such as, navigation, tracking, and routing in complex VLSI systems. The last is of particular interest to this work.

scholarly journals Fighting Deepfakes by Detecting GAN DCT Anomalies

2021 ◽  
Vol 7 (8) ◽  
pp. 128
Author(s):  
Oliver Giudice ◽  
Luca Guarnera ◽  
Sebastiano Battiato
Keyword(s):  
Neural Networks ◽  
Discrete Cosine Transform ◽  
Deep Neural Networks ◽  
Ad Hoc ◽  
State Of The Art ◽  
Private Life ◽  
Multimedia Content ◽  
Generative Adversarial Network ◽  
Detection Algorithms ◽  
Adversarial Network

To properly contrast the Deepfake phenomenon the need to design new Deepfake detection algorithms arises; the misuse of this formidable A.I. technology brings serious consequences in the private life of every involved person. State-of-the-art proliferates with solutions using deep neural networks to detect a fake multimedia content but unfortunately these algorithms appear to be neither generalizable nor explainable. However, traces left by Generative Adversarial Network (GAN) engines during the creation of the Deepfakes can be detected by analyzing ad-hoc frequencies. For this reason, in this paper we propose a new pipeline able to detect the so-called GAN Specific Frequencies (GSF) representing a unique fingerprint of the different generative architectures. By employing Discrete Cosine Transform (DCT), anomalous frequencies were detected. The β statistics inferred by the AC coefficients distribution have been the key to recognize GAN-engine generated data. Robustness tests were also carried out in order to demonstrate the effectiveness of the technique using different attacks on images such as JPEG Compression, mirroring, rotation, scaling, addition of random sized rectangles. Experiments demonstrated that the method is innovative, exceeds the state of the art and also give many insights in terms of explainability.

Role of General Adversarial Networks in Mammogram Analysis: A Review

2020 ◽  
Vol 16 (7) ◽  
pp. 863-877
Author(s):  
Annapoorani Gopal ◽  
Lathaselvi Gandhimaruthian ◽  
Javid Ali
Keyword(s):  
Breast Tumor ◽  
Deep Neural Networks ◽  
Training Data ◽  
Learning Technology ◽  
Breast Cancers ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Tumor Extraction

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.

Sign in / Sign up

Export Citation Format

Share Document