Fast Accurate and Automatic Brushstroke Extraction

Brushstrokes are viewed as the artist’s “handwriting” in a painting. In many applications such as style learning and transfer, mimicking painting, and painting authentication, it is highly desired to quantitatively and accurately identify brushstroke characteristics from old masters’ pieces using computer programs. However, due to the nature of hundreds or thousands of intermingling brushstrokes in the painting, it still remains challenging. This article proposes an efficient algorithm for brush Stroke extraction based on a Deep neural network, i.e., DStroke. Compared to the state-of-the-art research, the main merit of the proposed DStroke is to automatically and rapidly extract brushstrokes from a painting without manual annotation, while accurately approximating the real brushstrokes with high reliability. Herein, recovering the faithful soft transitions between brushstrokes is often ignored by the other methods. In fact, the details of brushstrokes in a master piece of painting (e.g., shapes, colors, texture, overlaps) are highly desired by artists since they hold promise to enhance and extend the artists’ powers, just like microscopes extend biologists’ powers. To demonstrate the high efficiency of the proposed DStroke, we perform it on a set of real scans of paintings and a set of synthetic paintings, respectively. Experiments show that the proposed DStroke is noticeably faster and more accurate at identifying and extracting brushstrokes, outperforming the other methods.

Download Full-text

GELU-Net: A Globally Encrypted, Locally Unencrypted Deep Neural Network for Privacy-Preserved Learning

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/547 ◽

2018 ◽

Cited By ~ 3

Author(s):

Qiao Zhang ◽

Cong Wang ◽

Hongyi Wu ◽

Chunsheng Xin ◽

Tran V. Phuong

Keyword(s):

Neural Network ◽

Data Aggregation ◽

Deep Neural Network ◽

State Of The Art ◽

The Other ◽

Computation Complexity ◽

Encrypted Data ◽

Deep Model ◽

Fundamental Challenge ◽

Main Strategy

Privacy is a fundamental challenge for a variety of smart applications that depend on data aggregation and collaborative learning across different entities. In this paper, we propose a novel privacy-preserved architecture where clients can collaboratively train a deep model while preserving the privacy of each client’s data. Our main strategy is to carefully partition a deep neural network to two non-colluding parties. One party performs linear computations on encrypted data utilizing a less complex homomorphic cryptosystem, while the other executes non-polynomial computations in plaintext but in a privacy-preserved manner. We analyze security and compare the communication and computation complexity with the existing approaches. Our extensive experiments on different datasets demonstrate not only stable training without accuracy loss, but also 14 to 35 times speedup compared to the state-of-the-art system.

Download Full-text

An Efficient Method for Detection of DDoS Attacks on the Web Using Deep Learning Algorithms

International Journal of Advanced Trends in Computer Science and Engineering ◽

10.30534/ijatcse/2021/271042021 ◽

2021 ◽

Vol 10 (4) ◽

pp. 2821-2829

Keyword(s):

Neural Network ◽

Deep Learning ◽

Deep Neural Network ◽

State Of The Art ◽

Ddos Attacks ◽

Problem Statement ◽

Neural Network Approach ◽

Learning Techniques ◽

Attack Data ◽

Deep Learning Neural Network

Recently, DDoS attacks is the most significant threat in network security. Both industry and academia are currently debating how to detect and protect against DDoS attacks. Many studies are provided to detect these types of attacks. Deep learning techniques are the most suitable and efficient algorithm for categorizing normal and attack data. Hence, a deep neural network approach is proposed in this study to mitigate DDoS attacks effectively. We used a deep learning neural network to identify and classify traffic as benign or one of four different DDoS attacks. We will concentrate on four different DDoS types: Slowloris, Slowhttptest, DDoS Hulk, and GoldenEye. The rest of the paper is organized as follow: Firstly, we introduce the work, Section 2 defines the related works, Section 3 presents the problem statement, Section 4 describes the proposed methodology, Section 5 illustrate the results of the proposed methodology and shows how the proposed methodology outperforms state-of-the-art work and finally Section VI concludes the paper.

Download Full-text

An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network

10.31219/osf.io/2zk6a ◽

2021 ◽

Author(s):

Anh Nguyen ◽

Khoa Pham ◽

Dat Ngo ◽

Thanh Ngo ◽

Lam Pham

Keyword(s):

Neural Network ◽

Supervised Classification ◽

Deep Neural Network ◽

State Of The Art ◽

Network Architectures ◽

Activation Functions ◽

Scene Classification ◽

Learning Network ◽

Deep Learning Network

This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU), Scaled Exponential Linear Unit (SELU), Gaussian Error Linear Unit (GELU), and the Inverse Square Root Linear Unit (ISRLU). To evaluate, experiments over two deep learning network architectures integrating these activation functions are conducted. The first model, basing on Multilayer Perceptron (MLP), is evaluated with MNIST dataset to perform these activation functions.Meanwhile, the second model, likely VGGish-based architecture, is applied for Acoustic Scene Classification (ASC) Task 1A in DCASE 2018 challenge, thus evaluate whether these activation functions work well in different datasets as well as different network architectures.

Download Full-text

Regularized Training and Tight Certification for Randomized Smoothed Classifier with Provable Robustness

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5798 ◽

2020 ◽

Vol 34 (04) ◽

pp. 3858-3865

Author(s):

Huijie Feng ◽

Chunpeng Wu ◽

Guoyang Chen ◽

Weifeng Zhang ◽

Yang Ning

Keyword(s):

Neural Network ◽

High Probability ◽

Deep Neural Network ◽

State Of The Art ◽

Computationally Efficient ◽

Base Classifier ◽

Training Scheme ◽

Adversarial Training ◽

Gaussian Perturbation ◽

Probabilistic Robustness

Recently smoothing deep neural network based classifiers via isotropic Gaussian perturbation is shown to be an effective and scalable way to provide state-of-the-art probabilistic robustness guarantee against ℓ2 norm bounded adversarial perturbations. However, how to train a good base classifier that is accurate and robust when smoothed has not been fully investigated. In this work, we derive a new regularized risk, in which the regularizer can adaptively encourage the accuracy and robustness of the smoothed counterpart when training the base classifier. It is computationally efficient and can be implemented in parallel with other empirical defense methods. We discuss how to implement it under both standard (non-adversarial) and adversarial training scheme. At the same time, we also design a new certification algorithm, which can leverage the regularization effect to provide tighter robustness lower bound that holds with high probability. Our extensive experimentation demonstrates the effectiveness of the proposed training and certification approaches on CIFAR-10 and ImageNet datasets.

Download Full-text

Novel Spatiotemporal Feature Extraction Parallel Deep Neural Network for Forecasting Confirmed Cases of Coronavirus Disease 2019

10.1101/2020.04.30.20086538 ◽

2020 ◽

Author(s):

Chiou-Jye Huang ◽

Yamin Shen ◽

Ping-Huan Kuo ◽

Yung-Hsiang Chen

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Absolute Error ◽

Mean Absolute Percentage Error ◽

The Other ◽

Percentage Error ◽

Model Assessment ◽

Absolute Percentage Error ◽

Spatiotemporal Feature ◽

The Mean

AbstractThe coronavirus disease 2019 pandemic continues as of March 26 and spread to Europe on approximately February 24. A report from April 29 revealed 1.26 million confirmed cases and 125 928 deaths in Europe. This study proposed a novel deep neural network framework, COVID-19Net, which parallelly combines a convolutional neural network (CNN) and bidirectional gated recurrent units (GRUs). Three European countries with severe outbreaks were studied—Germany, Italy, and Spain—to extract spatiotemporal feature and predict the number of confirmed cases. The prediction results acquired from COVID-19Net were compared to those obtained using a CNN, GRU, and CNN-GRU. The mean absolute error, mean absolute percentage error, and root mean square error, which are commonly used model assessment indices, were used to compare the accuracy of the models. The results verified that COVID-19Net was notably more accurate than the other models. The mean absolute percentage error generated by COVID-19Net was 1.447 for Germany, 1.801 for Italy, and 2.828 for Spain, which were considerably lower than those of the other models. This indicated that the proposed framework can accurately predict the accumulated number of confirmed cases in the three countries and serve as a crucial reference for devising public health strategies.

Download Full-text

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

10.36227/techrxiv.14100890 ◽

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.

Download Full-text

Generating Predictable and Adaptive Dialog Policies in Single- and Multi-domain Goal-oriented Dialog Systems

International Journal of Semantic Computing ◽

10.1142/s1793351x21400109 ◽

2021 ◽

Vol 15 (04) ◽

pp. 419-439

Author(s):

Nhat Le ◽

A. B. Siddique ◽

Fuad Jamour ◽

Samet Oymak ◽

Vagelis Hristidis

Keyword(s):

State Of The Art ◽

Directed Graphs ◽

Dependency Graph ◽

The Other ◽

Middle Ground ◽

User Characteristics ◽

Dialog Systems ◽

Dependency Graphs ◽

Novel Structure ◽

Art Research

Most existing commercial goal-oriented chatbots are diagram-based; i.e. they follow a rigid dialog flow to fill the slot values needed to achieve a user’s goal. Diagram-based chatbots are predictable, thus their adoption in commercial settings; however, their lack of flexibility may cause many users to leave the conversation before achieving their goal. On the other hand, state-of-the-art research chatbots use Reinforcement Learning (RL) to generate flexible dialog policies. However, such chatbots can be unpredictable, may violate the intended business constraints, and require large training datasets to produce a mature policy. We propose a framework that achieves a middle ground between the diagram-based and RL-based chatbots: we constrain the space of possible chatbot responses using a novel structure, the chatbot dependency graph, and use RL to dynamically select the best valid responses. Dependency graphs are directed graphs that conveniently express a chatbot’s logic by defining the dependencies among slots: all valid dialog flows are encapsulated in one dependency graph. Our experiments in both single-domain and multi-domain settings show that our framework quickly adapts to user characteristics and achieves up to 23.77% improved success rate compared to a state-of-the-art RL model.

Download Full-text

Image-Based Learning to Measure the Space Mean Speed on a Stretch of Road without the Need to Tag Images with Labels

Sensors ◽

10.3390/s19051227 ◽

2019 ◽

Vol 19 (5) ◽

pp. 1227 ◽

Cited By ~ 6

Author(s):

Jincheol Lee ◽

Seungbin Roh ◽

Johyun Shin ◽

Keemin Sohn

Keyword(s):

Neural Network ◽

Motion Capture ◽

Test Performance ◽

State Of The Art ◽

Manual Annotation ◽

Learning Models ◽

Traffic Conditions ◽

Adversarial Network ◽

Realistic Images ◽

Vehicle Movement

Space mean speed cannot be directly measured in the field, although it is a basic parameter that is used to evaluate traffic conditions. An end-to-end convolutional neural network (CNN) was adopted to measure the space mean speed based solely on two consecutive road images. However, tagging images with labels (=true space mean speeds) by manually positioning and tracking every vehicle on road images is a formidable task. The present study was focused on naïve animation images provided by a traffic simulator, because these contain perfect information concerning vehicle movement to attain labels. The animation images, however, seem far-removed from actual photos taken in the field. A cycle-consistent adversarial network (CycleGAN) bridged the reality gap by mapping the animation images into seemingly realistic images that could not be distinguished from real photos. A CNN model trained on the synthesized images was tested on real photos that had been manually labeled. The test performance was comparable to those of state-of-the-art motion-capture technologies. The proposed method showed that deep-learning models to measure the space mean speed could be trained without the need for time-consuming manual annotation.

Download Full-text

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

10.36227/techrxiv.14100890.v1 ◽

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

Download Full-text

Two particle picking procedures for filamentous proteins: SPHIRE-crYOLO filament mode and SPHIRE-STRIPER

10.1101/2020.02.28.969196 ◽

2020 ◽

Cited By ~ 1

Author(s):

Thorsten Wagner ◽

Luca Lusnig ◽

Sabrina Pospich ◽

Markus Stabrin ◽

Fabian Schönfeld ◽

...

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Molecular Complexes ◽

High Accuracy ◽

The Other ◽

Line Detection ◽

Data Sets ◽

Detection Approach ◽

Selection Of

AbstractStructure determination of filamentous molecular complexes involves the selection of filaments from cryo-EM micrographs. The automatic selection of helical specimens is particularly difficult and thus many challenging samples with issues such as contamination or aggregation are still manually picked. Here we present two approaches for selecting filamentous complexes: one uses a trained deep neural network to identify the filaments and is integrated in SPHIRE-crYOLO, the other one, called SPHIRE-STRIPER, is based on a classical line detection approach. The advantage of the crYOLO based procedure is that it accurately performs on very challenging data sets and selects filaments with high accuracy. Although STRIPER is less precise, the user benefits from less intervention, since in contrast to crYOLO, STRIPER does not require training. We evaluate the performance of both procedures on tobacco mosaic virus and filamentous F-actin data sets to demonstrate the robustness of each method.

Download Full-text