scholarly journals FET-GAN: Font and Effect Transfer via K-shot Adaptive Instance Normalization

2020 ◽  
Vol 34 (02) ◽  
pp. 1717-1724
Author(s):  
Wei Li ◽  
Yongxing He ◽  
Yanwei Qi ◽  
Zejian Li ◽  
Yongchuan Tang
Keyword(s):  
Experimental Validation ◽  
State Of The Art ◽  
Transfer Task ◽  
Labor Cost ◽  
Fine Tuning ◽  
Visual Effects ◽  
Generalization Ability ◽  
Text Content ◽  
Tuning Strategy ◽  
Chinese And English

Text effect transfer aims at learning the mapping between text visual effects while maintaining the text content. While remarkably successful, existing methods have limited robustness in font transfer and weak generalization ability to unseen effects. To address these problems, we propose FET-GAN, a novel end-to-end framework to implement visual effects transfer with font variation among multiple text effects domains. Our model achieves remarkable results both on arbitrary effect transfer between texts and effect translation from text to graphic objects. By a few-shot fine-tuning strategy, FET-GAN can generalize the transfer of the pre-trained model to the new effect. Through extensive experimental validation and comparison, our model advances the state-of-the-art in the text effect transfer task. Besides, we have collected a font dataset including 100 fonts of more than 800 Chinese and English characters. Based on this dataset, we demonstrated the generalization ability of our model by the application that complements the font library automatically by few-shot samples. This application is significant in reducing the labor cost for the font designer.

scholarly journals Backbone Cannot Be Trained at Once: Rolling Back to Pre-Trained Network for Person Re-Identification

2019 ◽  
Vol 33 ◽  
pp. 8859-8867 ◽  
Author(s):  
Youngmin Ro ◽  
Jongwon Choi ◽  
Dae Ung Jo ◽  
Byeongho Heo ◽  
Jongin Lim ◽  
...  
Keyword(s):  
Network Architecture ◽  
State Of The Art ◽  
Fine Tuning ◽  
Neural Network Architecture ◽  
Large Dataset ◽  
Low Level ◽  
Tuning Method ◽  
Improved Performance ◽  
High Level ◽  
Tuning Strategy

In person re-identification (ReID) task, because of its shortage of trainable dataset, it is common to utilize fine-tuning method using a classification network pre-trained on a large dataset. However, it is relatively difficult to sufficiently finetune the low-level layers of the network due to the gradient vanishing problem. In this work, we propose a novel fine-tuning strategy that allows low-level layers to be sufficiently trained by rolling back the weights of high-level layers to their initial pre-trained weights. Our strategy alleviates the problem of gradient vanishing in low-level layers and robustly trains the low-level layers to fit the ReID dataset, thereby increasing the performance of ReID tasks. The improved performance of the proposed strategy is validated via several experiments. Furthermore, without any addons such as pose estimation or segmentation, our strategy exhibits state-of-the-art performance using only vanilla deep convolutional neural network architecture.

scholarly journals Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models

2021 ◽  
Author(s):  
Shangwei Guo ◽  
Tianwei Zhang ◽  
Han Qiu ◽  
Yi Zeng ◽  
Tao Xiang ◽  
...  
Keyword(s):  
Intellectual Property ◽  
State Of The Art ◽  
Model Performance ◽  
Fine Tuning ◽  
Success Rates ◽  
Augmentation Techniques ◽  
Spatial Level ◽  
Tuning Strategy ◽  
Watermarking Scheme ◽  
Very High

Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechanisms by designing watermark removal attacks. However, these attacks mainly adopted sophisticated fine-tuning techniques, which have certain fatal drawbacks or unrealistic assumptions. In this paper, we propose a novel watermark removal attack from a different perspective. Instead of just fine-tuning the watermarked models, we design a simple yet powerful transformation algorithm by combining imperceptible pattern embedding and spatial-level transformations, which can effectively and blindly destroy the memorization of watermarked models to the watermark samples. We also introduce a lightweight fine-tuning strategy to preserve the model performance. Our solution requires much less resource or knowledge about the watermarking scheme than prior works. Extensive experimental results indicate that our attack can bypass state-of-the-art watermarking solutions with very high success rates. Based on our attack, we propose watermark augmentation techniques to enhance the robustness of existing watermarks.

scholarly journals New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Young Jae Kim ◽  
Jang Pyo Bae ◽  
Jun-Won Chung ◽  
Dong Kyun Park ◽  
Kwang Gi Kim ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Transfer Learning ◽  
Test Data ◽  
State Of The Art ◽  
Early Stage ◽  
Statistical Significance ◽  
Recall Rate ◽  
Training Data ◽  
Fine Tuning ◽  
Accuracy Evaluation

AbstractWhile colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.

scholarly journals Electrical Damping Assessment and Sensitivity Analysis of a Liquefied Natural Gas Plant: Experimental Validation

Energies ◽  
2020 ◽  
Vol 13 (16) ◽  
pp. 4084
Author(s):  
Lorenzo Bongini ◽  
Rosa Anna Mastromauro ◽  
Daniele Sgrò ◽  
Fabrizio Malvaldi
Keyword(s):  
Sensitivity Analysis ◽  
Control System ◽  
Natural Gas ◽  
Experimental Validation ◽  
Power Conversion ◽  
Liquefied Natural Gas ◽  
Fine Tuning ◽  
Simulation Platform ◽  
Electrical Damping ◽  
Conversion Stage

Liquefied Natural Gas (LNG) plants are commonly island-operated weak grids where the interaction of high-power Variable Frequency Drives (VFDs) with the Turbine-Generator (TG) units might cause Sub-Synchronous Torsional Interaction (SSTI) phenomena. SSTI phenomena can lead the LNG plant to instability conditions. Each LNG plant configuration is characterized by a risk level, which is considered high when the electrical damping at the TG Torsional Natural Frequencies (TNFs) is negative. Starting from a real case study, a detailed electromechanical model of an LNG plant is presented. The model is comprehensive of the control system of the power conversion stage and of the TG unit. Sensitivity analysis, performed on control system parameters, allows one to detect the parameters that impact the electrical damping and the stability of the overall LNG plant. A complete simulation platform is developed. Experimental results are carried out on a real LNG plant considering four different configurations. The theoretical model and the simulation platform allow one to estimate the electrical damping and the results are confirmed by the experimental validation. It is demonstrated that fine tuning of the power conversion stage control parameters can reduce the risk related to torsional instability.

scholarly journals Two-Stage Mask-RCNN Approach for Detecting and Segmenting the Optic Nerve Head, Optic Disc, and Optic Cup in Fundus Images

2020 ◽  
Vol 10 (11) ◽  
pp. 3833 ◽  
Author(s):  
Haidar Almubarak ◽  
Yakoub Bazi ◽  
Naif Alajlan
Keyword(s):  
Optic Nerve ◽  
Optic Disc ◽  
Optic Nerve Head ◽  
Fine Tuning ◽  
Fundus Images ◽  
Two Stage ◽  
Second Stage ◽  
Retinal Fundus Images ◽  
Tuning Strategy ◽  
Retinal Fundus

In this paper, we propose a method for localizing the optic nerve head and segmenting the optic disc/cup in retinal fundus images. The approach is based on a simple two-stage Mask-RCNN compared to sophisticated methods that represent the state-of-the-art in the literature. In the first stage, we detect and crop around the optic nerve head then feed the cropped image as input for the second stage. The second stage network is trained using a weighted loss to produce the final segmentation. To further improve the detection in the first stage, we propose a new fine-tuning strategy by combining the cropping output of the first stage with the original training image to train a new detection network using different scales for the region proposal network anchors. We evaluate the method on Retinal Fundus Images for Glaucoma Analysis (REFUGE), Magrabi, and MESSIDOR datasets. We used the REFUGE training subset to train the models in the proposed method. Our method achieved 0.0430 mean absolute error in the vertical cup-to-disc ratio (MAE vCDR) on the REFUGE test set compared to 0.0414 obtained using complex and multiple ensemble networks methods. The models trained with the proposed method transfer well to datasets outside REFUGE, achieving a MAE vCDR of 0.0785 and 0.077 on MESSIDOR and Magrabi datasets, respectively, without being retrained. In terms of detection accuracy, the proposed new fine-tuning strategy improved the detection rate from 96.7% to 98.04% on MESSIDOR and from 93.6% to 100% on Magrabi datasets compared to the reported detection rates in the literature.

On-device Prior Knowledge Incorporated Learning for Personalized Atrial Fibrillation Detection

2021 ◽  
Vol 20 (5s) ◽  
pp. 1-25
Author(s):  
Zhenge Jia ◽  
Yiyu Shi ◽  
Samir Saba ◽  
Jingtong Hu
Keyword(s):  
Atrial Fibrillation ◽  
Prior Knowledge ◽  
Domain Knowledge ◽  
Fine Tuning ◽  
Cardiac Monitoring ◽  
Patient Specific ◽  
Detection Accuracy ◽  
Specific Patient ◽  
Deep Model ◽  
Tuning Strategy

Atrial Fibrillation (AF), one of the most prevalent arrhythmias, is an irregular heart-rate rhythm causing serious health problems such as stroke and heart failure. Deep learning based methods have been exploited to provide an end-to-end AF detection by automatically extracting features from Electrocardiogram (ECG) signal and achieve state-of-the-art results. However, the pre-trained models cannot adapt to each patient’s rhythm due to the high variability of rhythm characteristics among different patients. Furthermore, the deep models are prone to overfitting when fine-tuned on the limited ECG of the specific patient for personalization. In this work, we propose a prior knowledge incorporated learning method to effectively personalize the model for patient-specific AF detection and alleviate the overfitting problems. To be more specific, a prior-incorporated portion importance mechanism is proposed to enforce the network to learn to focus on the targeted portion of the ECG, following the cardiologists’ domain knowledge in recognizing AF. A prior-incorporated regularization mechanism is further devised to alleviate model overfitting during personalization by regularizing the fine-tuning process with feature priors on typical AF rhythms of the general population. The proposed personalization method embeds the well-defined prior knowledge in diagnosing AF rhythm into the personalization procedure, which improves the personalized deep model and eliminates the workload of manually adjusting parameters in conventional AF detection method. The prior knowledge incorporated personalization is feasibly and semi-automatically conducted on the edge, device of the cardiac monitoring system. We report an average AF detection accuracy of 95.3% of three deep models over patients, surpassing the pre-trained model by a large margin of 11.5% and the fine-tuning strategy by 8.6%.

scholarly journals Differential Evolution: A Survey and Analysis

2018 ◽  
Vol 8 (10) ◽  
pp. 1945 ◽  
Author(s):  
Tarik Eltaeib ◽  
Ausif Mahmood
Keyword(s):  
Global Optimization ◽  
Differential Evolution ◽  
Optimization Problems ◽  
State Of The Art ◽  
Population Based ◽  
Vital Role ◽  
Fine Tuning ◽  
Control Parameters ◽  
Hybrid Techniques ◽  
Global Optimizer

Differential evolution (DE) has been extensively used in optimization studies since its development in 1995 because of its reputation as an effective global optimizer. DE is a population-based metaheuristic technique that develops numerical vectors to solve optimization problems. DE strategies have a significant impact on DE performance and play a vital role in achieving stochastic global optimization. However, DE is highly dependent on the control parameters involved. In practice, the fine-tuning of these parameters is not always easy. Here, we discuss the improvements and developments that have been made to DE algorithms. In particular, we present a state-of-the-art survey of the literature on DE and its recent advances, such as the development of adaptive, self-adaptive and hybrid techniques.

scholarly journals Covid-19 detection via deep neural network and occlusion sensitivity maps

2021 ◽  
Author(s):  
Noor Ahmad ◽  
Muhammad Aminu ◽  
Mohd Halim Mohd Noor
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Color Images ◽  
Fine Tuning ◽  
Training Dataset ◽  
Learning Approaches ◽  
Learning Models ◽  
Sensitivity Maps

Deep learning approaches have attracted a lot of attention in the automatic detection of Covid-19 and transfer learning is the most common approach. However, majority of the pre-trained models are trained on color images, which can cause inefficiencies when fine-tuning the models on Covid-19 images which are often grayscale. To address this issue, we propose a deep learning architecture called CovidNet which requires a relatively smaller number of parameters. CovidNet accepts grayscale images as inputs and is suitable for training with limited training dataset. Experimental results show that CovidNet outperforms other state-of-the-art deep learning models for Covid-19 detection.

scholarly journals Scanning electron microscope fine tuning using four-bar piezoelectric actuated mechanism

2018 ◽  
Vol 69 (1) ◽  
pp. 24-31
Author(s):  
Khaled S. Hatamleh ◽  
Qais A. Khasawneh ◽  
Adnan Al-Ghasem ◽  
Mohammad A. Jaradat ◽  
Laith Sawaqed ◽  
...  
Keyword(s):  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Inverse Kinematic ◽  
Fine Tuning ◽  
Electron Microscopes ◽  
Tuning Strategy ◽  
Scanning Electron Microscopes ◽  
Fine Tune ◽  
Kinematic Solution ◽  
Scanning Electron

Abstract Scanning Electron Microscopes are extensively used for accurate micro/nano images exploring. Several strategies have been proposed to fine tune those microscopes in the past few years. This work presents a new fine tuning strategy of a scanning electron microscope sample table using four bar piezoelectric actuated mechanisms. The introduced paper presents an algorithm to find all possible inverse kinematics solutions of the proposed mechanism. In addition, another algorithm is presented to search for the optimal inverse kinematic solution. Both algorithms are used simultaneously by means of a simulation study to fine tune a scanning electron microscope sample table through a pre-specified circular or linear path of motion. Results of the study shows that, proposed algorithms were able to minimize the power required to drive the piezoelectric actuated mechanism by a ratio of 97.5% for all simulated paths of motion when compared to general non-optimized solution.

scholarly journals Beyond Network Pruning: a Joint Search-and-Training Approach

2020 ◽  
Author(s):  
Xiaotong Lu ◽  
Han Huang ◽  
Weisheng Dong ◽  
Xin Li ◽  
Guangming Shi
Keyword(s):  
Random Perturbation ◽  
Search Space ◽  
Fine Tuning ◽  
Superior Performance ◽  
Network Pruning ◽  
Training Approach ◽  
Target Network ◽  
Tuning Strategy ◽  
Coarse To Fine ◽  
And Training

Network pruning has been proposed as a remedy for alleviating the over-parameterization problem of deep neural networks. However, its value has been recently challenged especially from the perspective of neural architecture search (NAS). We challenge the conventional wisdom of pruning-after-training by proposing a joint search-and-training approach that directly learns a compact network from the scratch. By treating pruning as a search strategy, we present two new insights in this paper: 1) it is possible to expand the search space of networking pruning by associating each filter with a learnable weight; 2) joint search-and-training can be conducted iteratively to maximize the learning efficiency. More specifically, we propose a coarse-to-fine tuning strategy to iteratively sample and update compact sub-network to approximate the target network. The weights associated with network filters will be accordingly updated by joint search-and-training to reflect learned knowledge in NAS space. Moreover, we introduce strategies of random perturbation (inspired by Monte Carlo) and flexible thresholding (inspired by Reinforcement Learning) to adjust the weight and size of each layer. Extensive experiments on ResNet and VGGNet demonstrate the superior performance of our proposed method on popular datasets including CIFAR10, CIFAR100 and ImageNet.

Sign in / Sign up

Export Citation Format

Share Document