• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.4
• /
• pp.511-523
• /
• 2023

Research on the integration of unmanned aerial vehicles and deep learning for reinforced concrete damage detection is actively underway. Convolutional neural networks have a high impact on the performance of image classification, detection, and segmentation as backbones. The MobileNet, a pre-trained convolutional neural network, is efficient as a backbone for an unmanned aerial vehicle-based damage detection model because it can achieve sufficient accuracy with low computational complexity. Analyzing vanilla convolutional neural networks and MobileNet under various conditions, MobileNet was evaluated to have a verification accuracy 6.0~9.0% higher than vanilla convolutional neural networks with 15.9~22.9% lower computational complexity. MobileNetV2, MobileNetV3Large and MobileNetV3Small showed almost identical maximum verification accuracy, and the optimal conditions for MobileNet's reinforced concrete damage image feature extraction were analyzed to be the optimizer RMSprop, no dropout, and average pooling. The maximum validation accuracy of 75.49% for 7 types of damage detection based on MobilenetV2 derived in this study can be improved by image accumulation and continuous learning.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.670-672
• /
• 2021

색소 세포성 모반과 악성 흑색종은 형태가 유사하지만 유해성의 측면에서 악성 흑색종은 암으로써 무해한 색소 세포성 모반에 비해 위험한 질환이다. 이에 기반하여 기존 연구에서 색소 세포성 모반과 악성 흑색종을 구분하기 위한 연구가 있었지만, 데이터를 취득하는 과정에서 많은 cost 가 필요하였다. 본 연구에서는 이를 개선하기 위해 두 병변의 dermatoscopic 영상을 분류 학습의 데이터로 사용하여 연구를 진행하였다. 학습을 위한 데이터는 오픈소스 dermatoscopic 데이터셋인 HAM10000을 사용하였으며 모델은 CNN 에서 개선된 MobileNetV2 를 사용하였다. 실험 결과, MobileNetV2 를 사용한 학습은 3-layer CNN 에 비해 15 분의 1 가량 적은 파라미터를 가졌으며, 검증 성능과 테스트 성능에서 93%에 근사하는 성능을 보였다. 본 연구는 이전 연구에 비해 cost 측면에서 큰 개선을 이루었으며, 상용화 가능한 분류 기법을 발견했다는 점을 시사한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1835-1845
• /
• 2021

To accurately identify black ice and warn the drivers of information in advance so they can control speed and take preventive measures. In this paper, we propose a lightweight black ice detection network based on infrared road images. A black ice recognition network model based on CNN transfer learning has been developed. Additionally, to further improve the accuracy of black ice recognition, an enhanced lightweight network based on MobileNetV2 has been developed. To reduce the amount of calculation, linear bottlenecks and inverse residuals was used, and four bottleneck groups were used. At the same time, to improve the recognition rate of the model, each bottleneck group was connected to a 3×3 convolutional layer to enhance regional feature extraction and increase the number of feature maps. Finally, a black ice recognition experiment was performed on the constructed infrared road black ice dataset. The network model proposed in this paper had an accurate recognition rate of 99.07% for black ice.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.154-156
• /
• 2021

Depth-wise separable convolution 은 컴퓨터 자원이 제한된 환경에서 기존의 standard convolution을 대체하는데 강력하고, 효과적인 대안으로 잘 알려져 있다.[1] MobileNetV2 에서는 Inverted residual block을 소개한다. 이는 depth-wise separable convolution으로 인해 생기는 손실, 즉 channel 간의 데이터를 조합해 새로운 feature를 만들어낼 기회를 잃어버릴 때, 이를 depth-wise separable convolution 양단에 point-wise convolution(1×1 convolution)을 사용함으로써 극복해낸 block이다.[1] 하지만 1×1 convolution은 채널 수에 의존적(dependent)인 특징을 갖고 있고, 따라서 결국 네트워크가 깊어지면 깊어질수록 효율적이고(efficient) 가벼운(light weight) 네트워크를 만드는데 병목 현상(bottleneck)을 일으키고 만다. 이 논문에서는 channel-wise squeeze and excitation block(CSE)을 통해 1×1 convolution을 부분적으로 대체하는 방법을 통해 이 병목 현상을 해결한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.504-506
• /
• 2022

최근 인공지능 기술의 발달에 따라 여러 분야에 인공지능 기술이 활발히 응용되고 있다. 그중 안전 관리 분야에서 사람 인식을 통한 안전 관리 시스템의 지속적인 개발이 요구되고 있다. 그러나 실내 한정된 공간에서 사람들의 밀집도가 높은 경우 오브젝트의 중복도가 높아져 인식 성능이 낮아질 수 있다. 이를 해결하기 위해 본 논문은 사람의 밀집도가 높은 실내 환경에서 기존 객체 인식 기법의 성능을 분석하였다. 그리고 이러한 제한적인 환경에서 최적의 좋은 성능을 보일 수 있는 SSDLite와 MobileNetV2 모델을 기반으로 soft-NMS 기법을 적용하여 성능을 분석하였다.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.685-690
• /
• 2020

We propose an efficient convolutional neural network with much lower computational complexity and higher accuracy based on MobileNet V2 for mobile or edge devices. The proposed network consists of bottleneck layers with larger expansion factors and adjusted number of channels, and excludes a few layers, and therefore, the computational complexity is reduced by half. The performance the proposed network is verified by measuring the accuracy and execution times by CPU and GPU using ImageNet100 dataset. In addition, the execution time on GPU depends on the CNN architecture.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.451-452
• /
• 2023

최근 CNN 이 다양한 산업에 확산되고 있으며, IoT 기기 및 엣지 컴퓨팅에 적합한 경량 모델에 대한 연구가 급증하고 있다. 본 논문에서는 CNN 모델의 파라미터 비트 연산을 위한 자동화 프레임워크를 제안하고, 파라미터 비트와 모델 정확도 사이의 관계를 실험 및 연구한다. 제안된 프레임워크는 하위 n- bit 를 0 으로 설정하여 정보 손실 발생시킴으로써 ImageNet 데이터셋으로 사전 학습된 CNN 모델의 파라미터와 정확도의 강인성을 비트 단위로 체계적으로 실험할 수 있다. 우리는 비트 연산을 수행한 파라미터로 InceptionV3, InceptionResnetV2, ResNet50, Xception, DenseNet121, MobileNetV1, MobileNetV2 모델의 정확도를 평가한다. 실험 결과는 성능이 낮은 모델일수록 파라미터와 정확도 간의 강인성이 높아 성능이 좋은 모델보다 정확도를 유지하는 비트 수가 적다는 것을 보여준다.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.67-79
• /
• 2023

In the image field, data augmentation refers to increasing the amount of data through an editing method such as rotating or cropping a photo. In this study, a generative adversarial network (GAN) image was created using CycleGAN, and various colors of dogs were reflected through data augmentation. In particular, dog data from the Stanford Dogs Dataset and Oxford-IIIT Pet Dataset were used, and 10 breeds of dog, corresponding to 300 images each, were selected. Subsequently, a GAN image was generated using CycleGAN, and four learning groups were established: 2,000 original photos (group I); 2,000 original photos + 1,000 GAN images (group II); 3,000 original photos (group III); and 3,000 original photos + 1,000 GAN images (group IV). The amount of data in each learning group was augmented using existing data augmentation methods such as rotating, cropping, erasing, and distorting. The augmented photo data were used to train the MobileNet_v3_Large, ResNet-152, InceptionResNet_v2, and NASNet_Large frameworks to evaluate the classification accuracy and loss. The top-3 accuracy for each deep neural network model was as follows: MobileNet_v3_Large of 86.4% (group I), 85.4% (group II), 90.4% (group III), and 89.2% (group IV); ResNet-152 of 82.4% (group I), 83.7% (group II), 84.7% (group III), and 84.9% (group IV); InceptionResNet_v2 of 90.7% (group I), 88.4% (group II), 93.3% (group III), and 93.1% (group IV); and NASNet_Large of 85% (group I), 88.1% (group II), 91.8% (group III), and 92% (group IV). The InceptionResNet_v2 model exhibited the highest image classification accuracy, and the NASNet_Large model exhibited the highest increase in the accuracy owing to data augmentation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.570-590
• /
• 2024

Breast cancer ranks among the most prevalent forms of malignancy and foremost cause of death by cancer worldwide. It is not preventable. Early and precise detection is the only remedy for lowering the rate of mortality and improving the probability of survival for victims. In contrast to present procedures, thermography aids in the early diagnosis of cancer and thereby saves lives. But the accuracy experiences detrimental impact by low sensitivity for small and deep tumours and the subjectivity by physicians in interpreting the images. Employing deep learning approaches for cancer detection can enhance the efficacy. This study explored the utilization of thermography in early identification of breast cancer with the use of a publicly released dataset known as the DMR-IR dataset. For this purpose, we employed a novel approach that entails the utilization of a pre-trained MobileNetV2 model and fine tuning it through transfer learning techniques. We created three models using MobileNetV2: one was a baseline transfer learning model with weights trained from ImageNet dataset, the second was a fine-tuned model with an adaptive learning rate, and the third utilized early stopping with callbacks during fine-tuning. The results showed that the proposed methods achieved average accuracy rates of 85.15%, 95.19%, and 98.69%, respectively, with various performance indicators such as precision, sensitivity and specificity also being investigated.