Research on clothing patterns generation based on multi-scales self-attention improved generative adversarial network

PurposeClothing patterns play a dominant role in costume design and have become an important link in the perception of costume art. Conventional clothing patterns design relies on experienced designers. Although the quality of clothing patterns is very high on conventional design, the input time and output amount ratio is relative low for conventional design. In order to break through the bottleneck of conventional clothing patterns design, this paper proposes a novel way based on generative adversarial network (GAN) model for automatic clothing patterns generation, which not only reduces the dependence of experienced designer, but also improve the input-output ratio.Design/methodology/approachIn view of the fact that clothing patterns have high requirements for global artistic perception and local texture details, this paper improves the conventional GAN model from two aspects: a multi-scales discriminators strategy is introduced to deal with the local texture details; and the self-attention mechanism is introduced to improve the global artistic perception. Therefore, the improved GAN called multi-scales self-attention improved generative adversarial network (MS-SA-GAN) model, which is used for high resolution clothing patterns generation.FindingsTo verify the feasibility and effectiveness of the proposed MS-SA-GAN model, a crawler is designed to acquire standard clothing patterns dataset from Baidu pictures, and a comparative experiment is conducted on our designed clothing patterns dataset. In experiments, we have adjusted different parameters of the proposed MS-SA-GAN model, and compared the global artistic perception and local texture details of the generated clothing patterns.Originality/valueExperimental results have shown that the clothing patterns generated by the proposed MS-SA-GAN model are superior to the conventional algorithms in some local texture detail indexes. In addition, a group of clothing design professionals is invited to evaluate the global artistic perception through a valence-arousal scale. The scale results have shown that the proposed MS-SA-GAN model achieves a better global art perception.

Download Full-text

Electronic component detection based on image sample generation

Soldering & Surface Mount Technology ◽

10.1108/ssmt-08-2020-0036 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Hao Wu ◽

Quanquan Lv ◽

Jiankang Yang ◽

Xiaodong Yan ◽

Xiangrong Xu

Keyword(s):

Deep Learning ◽

Printed Circuit Board ◽

Training Model ◽

Circuit Board ◽

Electronic Components ◽

Generative Adversarial Network ◽

Content Type ◽

Real Samples ◽

Adversarial Network ◽

Defect Recognition

Purpose This paper aims to propose a deep learning model that can be used to expand the number of samples. In the process of manufacturing and assembling electronic components on the printed circuit board in the surface mount technology production line, it is relatively easy to collect non-defective samples, but it is difficult to collect defective samples within a certain period of time. Therefore, the number of non-defective components is much greater than the number of defective components. In the process of training the defect detection method of electronic components based on deep learning, a large number of defective and non-defective samples need to be input at the same time. Design/methodology/approach To obtain enough electronic components samples required for training, a method based on the generative adversarial network (GAN) to generate training samples is proposed, and then the generated samples and real samples are used to train the convolutional neural networks (CNN) together to obtain the best detection results. Findings The experimental results show that the defect recognition method using GAN and CNN can not only expand the sample images of the electronic components required for the training model but also accurately classify the defect types. Originality/value To solve the problem of unbalanced sample types in component inspection, a GAN-based method is proposed to generate different types of training component samples and then the generated samples and real samples are used to train the CNN together to obtain the best detection results.

Download Full-text

Artificial intelligence in the fashion industry: consumer responses to generative adversarial network (GAN) technology

International Journal of Retail & Distribution Management ◽

10.1108/ijrdm-03-2020-0091 ◽

2020 ◽

Vol 49 (1) ◽

pp. 61-80

Author(s):

Kwonsang Sohn ◽

Christine Eunyoung Sung ◽

Gukwon Koo ◽

Ohbyung Kwon

Keyword(s):

Artificial Intelligence ◽

Willingness To Pay ◽

Fashion Industry ◽

Generative Adversarial Network ◽

Experimental Conditions ◽

Content Type ◽

Consumer Responses ◽

Adversarial Network ◽

Consumption Values ◽

Artificial Intelligence Technology

PurposeThis study examines consumers' evaluations of product consumption values, purchase intentions and willingness to pay for fashion products designed using generative adversarial network (GAN), an artificial intelligence technology. This research investigates differences between consumers' evaluations of a GAN-generated product and a non-GAN-generated product and tests whether disclosing the use of GAN technology affects consumers' evaluations.Design/methodology/approachSample products were developed as experimental stimuli using cycleGAN. Data were collected from 163 members of Generation Y. Participants were assigned to one of the three experimental conditions (i.e. non-GAN-generated images, GAN-generated images with disclosure and GAN-generated images without disclosure). Regression analysis and ANOVA were used to test the hypotheses.FindingsFunctional, social and epistemic consumption values positively affect willingness to pay in the GAN-generated products. Relative to non-GAN-generated products, willingness to pay is significantly higher for GAN-generated products. Moreover, evaluations of functional value, emotional value and willingness to pay are highest when GAN technology is used, but not disclosed.Originality/valueThis study evaluates the utility of GANs from consumers' perspective based on the perceived value of GAN-generated product designs. Findings have practical implications for firms that are considering using GANs to develop products for the retail fashion market.

Download Full-text

Transfer Learning for Toxoplasma gondii Recognition

mSystems ◽

10.1128/msystems.00445-19 ◽

2020 ◽

Vol 5 (1) ◽

Author(s):

Sen Li ◽

Aijia Li ◽

Diego Alejandro Molina Lara ◽

Jorge Enrique Gómez Marín ◽

Mario Juhas ◽

...

Keyword(s):

Deep Learning ◽

Toxoplasma Gondii ◽

Transfer Learning ◽

Cluster Algorithm ◽

High Accuracy ◽

Generative Adversarial Network ◽

Content Type ◽

Microscopic Images ◽

Adversarial Network ◽

Content Identification

ABSTRACT Toxoplasma gondii, one of the world’s most common parasites, can infect all types of warm-blooded animals, including one-third of the world’s human population. Most current routine diagnostic methods are costly, time-consuming, and labor-intensive. Although T. gondii can be directly observed under the microscope in tissue or spinal fluid samples, this form of identification is difficult and requires well-trained professionals. Nevertheless, the traditional identification of parasites under the microscope is still performed by a large number of laboratories. Novel, efficient, and reliable methods of T. gondii identification are therefore needed, particularly in developing countries. To this end, we developed a novel transfer learning-based microscopic image recognition method for T. gondii identification. This approach employs the fuzzy cycle generative adversarial network (FCGAN) with transfer learning utilizing knowledge gained by parasitologists that Toxoplasma is banana or crescent shaped. Our approach aims to build connections between microscopic and macroscopic associated objects by embedding the fuzzy C-means cluster algorithm into the cycle generative adversarial network (Cycle GAN). Our approach achieves 93.1% and 94.0% detection accuracy for ×400 and ×1,000 Toxoplasma microscopic images, respectively. We showed the high accuracy and effectiveness of our approach in newly collected unlabeled Toxoplasma microscopic images, compared to other currently available deep learning methods. This novel method for Toxoplasma microscopic image recognition will open a new window for developing cost-effective and scalable deep learning-based diagnostic solutions, potentially enabling broader clinical access in developing countries. IMPORTANCE Toxoplasma gondii, one of the world’s most common parasites, can infect all types of warm-blooded animals, including one-third of the world’s human population. Artificial intelligence (AI) could provide accurate and rapid diagnosis in fighting Toxoplasma. So far, none of the previously reported deep learning methods have attempted to explore the advantages of transfer learning for Toxoplasma detection. The knowledge from parasitologists is that the Toxoplasma parasite is generally banana or crescent shaped. Based on this, we built connections between microscopic and macroscopic associated objects by embedding the fuzzy C-means cluster algorithm into the cycle generative adversarial network (Cycle GAN). Our approach achieves high accuracy and effectiveness in ×400 and ×1,000 Toxoplasma microscopic images.

Download Full-text

Depth from stacked light field images using generative adversarial network

Electronic Imaging ◽

10.2352/issn.2470-1173.2019.11.ipas-270 ◽

2019 ◽

Vol 2019 (11) ◽

pp. 270-1-270-8

Author(s):

Ji-Hun Mun ◽

Yo-Sung Ho

Keyword(s):

Light Field ◽

Generative Adversarial Network ◽

Adversarial Network

Download Full-text

Flight Trajectory Pattern Generalization and Abnormal Flight Detection with Generative Adversarial Network

AIAA Scitech 2021 Forum ◽

10.2514/6.2021-0775 ◽

2021 ◽

Author(s):

Muhammet Aksoy ◽

Orhan Ozdemir ◽

Guney Guner ◽

Baris Baspinar ◽

Emre Koyuncu

Keyword(s):

Flight Trajectory ◽

Generative Adversarial Network ◽

Pattern Generalization ◽

Adversarial Network ◽

Trajectory Pattern

Download Full-text

ORGANIC (1).pdf

10.26434/chemrxiv.5309668.v1 ◽

2017 ◽

Author(s):

Benjamin Sanchez-Lengeling ◽

Carlos Outeiral ◽

Gabriel L. Guimaraes ◽

Alan Aspuru-Guzik

Keyword(s):

Machine Learning ◽

Learning Community ◽

Chemical Species ◽

Material Design ◽

Organic Photovoltaic ◽

Generative Adversarial Networks ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Adversarial Networks ◽

Photovoltaic Material

Molecular discovery seeks to generate chemical species tailored to very specific needs. In this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative Adversarial Networks (ORGAN), capable of producing a distribution over molecular space that matches with a certain set of desirable metrics. This methodology combines two successful techniques from the machine learning community: a Generative Adversarial Network (GAN), to create non-repetitive sensible molecular species, and Reinforcement Learning (RL), to bias this generative distribution towards certain attributes. We explore several applications, from optimization of random physicochemical properties to candidates for drug discovery and organic photovoltaic material design.

Download Full-text

Completely Unsupervised Phoneme Recognition by a Generative Adversarial Network Harmonized with Iteratively Refined Hidden Markov Models

10.21437/interspeech.2019-2068 ◽

2019 ◽

Author(s):

Kuan-Yu Chen ◽

Che-Ping Tsai ◽

Da-Rong Liu ◽

Hung-Yi Lee ◽

Lin-shan Lee

Keyword(s):

Hidden Markov Models ◽

Markov Models ◽

Hidden Markov ◽

Phoneme Recognition ◽

Generative Adversarial Network ◽

Adversarial Network

Download Full-text

Role of General Adversarial Networks in Mammogram Analysis: A Review

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405614666191115102318 ◽

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.

Download Full-text