• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.55-67
• /
• 2023

Lightweight face recognition models, as one of the most popular and long-standing topics in the field of computer vision, has achieved vigorous development and has been widely used in many real-world applications due to fewer number of parameters, lower floating-point operations, and smaller model size. However, few surveys reviewed lightweight models and reimplemented these lightweight models by using the same calculating resource and training dataset. In this survey article, we present a comprehensive review about the recent research advances on the end-to-end efficient lightweight face recognition models and reimplement several of the most popular models. To start with, we introduce the overview of face recognition with lightweight models. Then, based on the construction of models, we categorize the lightweight models into: (1) artificially designing lightweight FR models, (2) pruned models to face recognition, (3) efficient automatic neural network architecture design based on neural architecture searching, (4) Knowledge distillation and (5) low-rank decomposition. As an example, we also introduce the SqueezeFaceNet and EfficientFaceNet by pruning SqueezeNet and EfficientNet. Additionally, we reimplement and present a detailed performance comparison of different lightweight models on the nine different test benchmarks. At last, the challenges and future works are provided. There are three main contributions in our survey: firstly, the categorized lightweight models can be conveniently identified so that we can explore new lightweight models for face recognition; secondly, the comprehensive performance comparisons are carried out so that ones can choose models when a state-of-the-art end-to-end face recognition system is deployed on mobile devices; thirdly, the challenges and future trends are stated to inspire our future works.

• 센서학회지
• /
• 제30권5호
• /
• pp.286-289
• /
• 2021

Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.

• 한국전자통신학회논문지
• /
• 제17권1호
• /
• pp.105-110
• /
• 2022

교통 표지 인식은 교통 관련 문제를 해결하는 데 중요한 역할을 한다. 교통 표지 인식 및 분류 시스템은 교통안전, 교통 모니터링, 자율주행 서비스 및 자율주행 차의 핵심 구성 요소이다. 휴대용 장치에 적용할 수 있는 경량 모델은 설계 의제의 필수 측면이다. 우리는 교통 표지 인식 시스템을 위한 잔여 블록이 있는 경량 합성곱 신경망 모델을 제안한다. 제안된 모델은 공개적으로 사용 가능한 벤치마크 데이터에서 매우 경쟁력 있는 결과를 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• 로봇학회논문지
• /
• 제12권4호
• /
• pp.432-440
• /
• 2017

In this paper, we propose a jellyfish distribution recognition and monitoring system using a UAV (unmanned aerial vehicle). The UAV was designed to satisfy the requirements for flight in ocean environment. The target jellyfish, Aurelia aurita, is recognized through convolutional neural network and its distribution is calculated. The modified deep neural network architecture has been developed to have reliable recognition accuracy and fast operation speed. Recognition speed is about 400 times faster than GoogLeNet by using a lightweight network architecture. We also introduce the method for selecting candidates to be used as inputs to the proposed network. The recognition accuracy of the jellyfish is improved by removing the probability value of the meaningless class among the probability vectors of the evaluated input image and re-evaluating it by normalization. The jellyfish distribution is calculated based on the unit jellyfish image recognized. The distribution level is defined by using the novelty concept of the distribution map buffer.

• Journal of Multimedia Information System
• /
• 제8권4호
• /
• pp.251-258
• /
• 2021

In 2019, a novel coronavirus (COVID-19) outbreak started in China and spread all over the world. The countries went into lockdown and closed their borders to minimize the spread of the virus. Shortage of testing kits and trained clinicians, motivate researchers and computer scientists to look for ways to automatically diagnose the COVID-19 patient using X-ray and ease the burden on the healthcare system. In recent years, multiple frameworks are presented but most of them are trained on a very small dataset which makes clinicians adamant to use it. In this paper, we have presented a lightweight deep learning base automatic COVID-19 detection system. We trained our model on more than 22,000 dataset X-ray samples. The proposed model achieved an overall accuracy of 96.88% with a sensitivity of 91.55%.

• Smart Structures and Systems
• /
• 제13권1호
• /
• pp.81-98
• /
• 2014

This paper presents the elastic buckling of smart lightweight column structures integrated with a pair of surface piezoelectric layers using artificial intelligence. The finite element modeling of Smart lightweight columns is found using $ANSYS^{(R)}$ software. Then, the first buckling load of the structure is calculated using eigenvalue buckling analysis. To determine the accuracy of the present finite element analysis, a compression study is carried out with literature. Later, parametric studies for length variations, width, and thickness of the elastic core and of the piezoelectric outer layers are performed and the associated buckling load data sets for artificial intelligence are gathered. Finally, the application of soft computing-based methods including artificial neural network (ANN), fuzzy inference system (FIS), and adaptive neuro fuzzy inference system (ANFIS) were carried out. A comparative study is then made between the mentioned soft computing methods and the performance of the models is evaluated using statistic measurements. The comparison of the results reveal that, the ANFIS model with Gaussian membership function provides high accuracy on the prediction of the buckling load in smart lightweight columns, providing better predictions compared to other methods. However, the results obtained from the ANN model using the feed-forward algorithm are also accurate and reliable.

• 한국구조물진단유지관리공학회 논문집
• /
• 제24권3호
• /
• pp.18-25
• /
• 2020

경량혼합토의 일축압축강도는 배합비에 크게 의존한다. 경량혼합토와 다양한 경량혼합토의 구성성분들의 관계를 특징짓기 위한 기존연구에서는 시험을 통한 회귀모델을 사용하여 정규화계수를 제안하였다. 그러나 실내시험에서 얻은 결과는 재료와 배합비사이의 관계가 복잡하기 때문에 일정한 예측의 정확도를 기대할 수 없다. 이 연구에서는 다양한 배합조건에서 수행된 실내시험결과를 바탕으로 심층신경망 모델을 적용함으로써 경량혼합토의 일축압축강도를 예측하였다. 제안된 심층신경망 모델을 사용함으로써 설계 배합조건으로 구성된 경량혼합토의 일축압축강도 값을 합리적으로 산정할 수 있다.

• 방송공학회논문지
• /
• 제26권6호
• /
• pp.778-789
• /
• 2021

최근 다양한 분야에서 뛰어난 성능을 나타내는 Convolutional Neural Network(CNN)모델을 모바일 기기에서 사용하기 위한 다양한 연구가 진행되고 있다. 기존의 CNN 모델은 모바일 장비에서 사용하기에는 가중치의 크기가 크고 연산복잡도가 높다는 문제점이 있다. 이를 해결하기 위해 가중치의 표현 비트를 낮추는 가중치 양자화를 포함한 여러 경량화 방법들이 등장하였다. 많은 방법들이 다양한 모델에서 적은 정확도 손실과 높은 압축률을 나타냈지만, 대부분의 압축 모델들은 정확도 손실을 복구하기 위한 재학습 과정을 포함시켰다. 재학습 과정은 압축된 모델의 정확도 손실을 최소화하지만 많은 시간과 데이터를 필요로 하는 작업이다. Weight Quantization이후 각 층의 가중치는 정수형 행렬로 나타나는데 이는 이미지의 형태와 유사하다. 본 논문에서는 Weight Quantization이후 각 층의 정수 가중치 행렬을 이미지의 형태로 비디오 코덱을 사용하여 압축하는 방법을 제안한다. 제안하는 방법의 성능을 검증하기 위해 ImageNet과 Places365 데이터 셋으로 학습된 VGG16, Resnet50, Resnet18모델에 실험을 진행하였다. 그 결과 다양한 모델에서 2%이하의 정확도 손실과 높은 압축 효율을 달성했다. 또한, 재학습 과정을 제외한 압축방법인 No Fine-tuning Pruning(NFP)와 ThiNet과의 성능비교 결과 2배 이상의 압축효율이 있음을 검증했다.

• Journal of Information Processing Systems
• /
• 제20권3호
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.