• Title/Summary/Keyword: 경량화 딥러닝 모델

Search Result 56, Processing Time 0.027 seconds

Text Classification Using Heterogeneous Knowledge Distillation

  • Yu, Yerin;Kim, Namgyu
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.10
    • /
    • pp.29-41
    • /
    • 2022
  • Recently, with the development of deep learning technology, a variety of huge models with excellent performance have been devised by pre-training massive amounts of text data. However, in order for such a model to be applied to real-life services, the inference speed must be fast and the amount of computation must be low, so the technology for model compression is attracting attention. Knowledge distillation, a representative model compression, is attracting attention as it can be used in a variety of ways as a method of transferring the knowledge already learned by the teacher model to a relatively small-sized student model. However, knowledge distillation has a limitation in that it is difficult to solve problems with low similarity to previously learned data because only knowledge necessary for solving a given problem is learned in a teacher model and knowledge distillation to a student model is performed from the same point of view. Therefore, we propose a heterogeneous knowledge distillation method in which the teacher model learns a higher-level concept rather than the knowledge required for the task that the student model needs to solve, and the teacher model distills this knowledge to the student model. In addition, through classification experiments on about 18,000 documents, we confirmed that the heterogeneous knowledge distillation method showed superior performance in all aspects of learning efficiency and accuracy compared to the traditional knowledge distillation.

Application and Performance Analysis of Double Pruning Method for Deep Neural Networks (심층신경망의 더블 프루닝 기법의 적용 및 성능 분석에 관한 연구)

  • Lee, Seon-Woo;Yang, Ho-Jun;Oh, Seung-Yeon;Lee, Mun-Hyung;Kwon, Jang-Woo
    • Journal of Convergence for Information Technology
    • /
    • v.10 no.8
    • /
    • pp.23-34
    • /
    • 2020
  • Recently, the artificial intelligence deep learning field has been hard to commercialize due to the high computing power and the price problem of computing resources. In this paper, we apply a double pruning techniques to evaluate the performance of the in-depth neural network and various datasets. Double pruning combines basic Network-slimming and Parameter-prunning. Our proposed technique has the advantage of reducing the parameters that are not important to the existing learning and improving the speed without compromising the learning accuracy. After training various datasets, the pruning ratio was increased to reduce the size of the model.We confirmed that MobileNet-V3 showed the highest performance as a result of NetScore performance analysis. We confirmed that the performance after pruning was the highest in MobileNet-V3 consisting of depthwise seperable convolution neural networks in the Cifar 10 dataset, and VGGNet and ResNet in traditional convolutional neural networks also increased significantly.

Performance Analysis of Optical Camera Communication with Applied Convolutional Neural Network (합성곱 신경망을 적용한 Optical Camera Communication 시스템 성능 분석)

  • Jong-In Kim;Hyun-Sun Park;Jung-Hyun Kim
    • Smart Media Journal
    • /
    • v.12 no.3
    • /
    • pp.49-59
    • /
    • 2023
  • Optical Camera Communication (OCC), known as the next-generation wireless communication technology, is currently under extensive research. The performance of OCC technology is affected by the communication environment, and various strategies are being studied to improve it. Among them, the most prominent method is applying convolutional neural networks (CNN) to the receiver of OCC using deep learning technology. However, in most studies, CNN is simply used to detect the transmitter. In this paper, we experiment with applying the convolutional neural network not only for transmitter detection but also for the Rx demodulation system. We hypothesize that, since the data images of the OCC system are relatively simple to classify compared to other image datasets, high accuracy results will appear in most CNN models. To prove this hypothesis, we designed and implemented an OCC system to collect data and applied it to 12 different CNN models for experimentation. The experimental results showed that not only high-performance CNN models with many parameters but also lightweight CNN models achieved an accuracy of over 99%. Through this, we confirmed the feasibility of applying the OCC system in real-time on mobile devices such as smartphones.

Real-time Single Image Super Resolution in Mobile Devices (모바일 단말에서 실시간으로 동작하는 초고해상화 기술 개발)

  • Kim, Sungjei;Jeong, Jinwoo;GANZORIG GANKHUYAG
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2022.11a
    • /
    • pp.42-43
    • /
    • 2022
  • 본 논문은 모바일 단말에서 실시간으로 동작하는 딥러닝 기반 경량 초고해상화 기술에 관한 내용이다. 대용량 3차원 메쉬 모델의 비실시간 압축은 실시간 스트리밍 응용 시나리오에서 제약점으로 작용하고 있고, 본 논문에서는 두 입력 텐서의 차원을 일치시켜야 하는 element-wise 덧셈 대신 concatenation을 활용해 연산량을 개선하고, float-to-int8 양자화 과정에서 발생하는 오차를 줄이기 위해 weight clipping 및 regularization 기법을 활용해 초고해상화 화질 성능을 개선하였다. 제안하는 알고리즘은 기존 모바일 초고해상화 기술을 화질 측면에서 0.12dB, 처리 속도 측면에서 13.6ms 개선하였고, Mobile AI & AIM 2022 실시간 이미지 초고해상화 대회에서 1등을 수상하였다.

  • PDF

Transformer and Spatial Pyramid Pooling based YOLO network for Object Detection (객체 검출을 위한 트랜스포머와 공간 피라미드 풀링 기반의 YOLO 네트워크)

  • Kwon, Oh-Jun;Jeong, Je-Chang
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • fall
    • /
    • pp.113-116
    • /
    • 2021
  • 일반적으로 딥러닝 기반의 객체 검출(Object Detection)기법은 합성곱 신경망(Convolutional Neural Network, CNN)을 통해 입력된 영상의 특징(Feature)을 추출하여 이를 통해 객체 검출을 수행한다. 최근 자연어 처리 분야에서 획기적인 성능을 보인 트랜스포머(Transformer)가 영상 분류, 객체 검출과 같은 컴퓨터 비전 작업을 수행하는데 있어 경쟁력이 있음이 드러나고 있다. 본 논문에서는 YOLOv4-CSP의 CSP 블록을 개선한 one-stage 방식의 객체 검출 네트워크를 제안한다. 개선된 CSP 블록은 트랜스포머(Transformer)의 멀티 헤드 어텐션(Multi-Head Attention)과 CSP 형태의 공간 피라미드 풀링(Spatial Pyramid Pooling, SPP) 연산을 기반으로 네트워크의 Backbone과 Neck에서의 feature 학습을 돕는다. 본 실험은 MSCOCO test-dev2017 데이터 셋으로 평가하였으며 제안하는 네트워크는 YOLOv4-CSP의 경량화 모델인 YOLOv4s-mish에 대하여 평균 정밀도(Average Precision, AP)기준 2.7% 향상된 검출 정확도를 보인다.

  • PDF

Simplification Method for Lightweighting of Underground Geospatial Objects in a Mobile Environment (모바일 환경에서 지하공간객체의 경량화를 위한 단순화 방법)

  • Jong-Hoon Kim;Yong-Tae Kim;Hoon-Joon Kouh
    • Journal of Industrial Convergence
    • /
    • v.20 no.12
    • /
    • pp.195-202
    • /
    • 2022
  • Underground Geospatial Information Map Management System(UGIMMS) integrates various underground facilities in the underground space into 3D mesh data, and supports to check the 3D image and location of the underground facilities in the mobile app. However, there is a problem that it takes a long time to run in the app because various underground facilities can exist in some areas executed by the app and can be seen layer by layer. In this paper, we propose a deep learning-based K-means vertex clustering algorithm as a method to reduce the execution time in the app by reducing the size of the data by reducing the number of vertices in the 3D mesh data within the range that does not cause a problem in visibility. First, our proposed method obtains refined vertex feature information through a deep learning encoder-decoder based model. And second, the method was simplified by grouping similar vertices through K-means vertex clustering using feature information. As a result of the experiment, when the vertices of various underground facilities were reduced by 30% with the proposed method, the 3D image model was slightly deformed, but there was no missing part, so there was no problem in checking it in the app.

Compression of DNN Integer Weight using Video Encoder (비디오 인코더를 통한 딥러닝 모델의 정수 가중치 압축)

  • Kim, Seunghwan;Ryu, Eun-Seok
    • Journal of Broadcast Engineering
    • /
    • v.26 no.6
    • /
    • pp.778-789
    • /
    • 2021
  • Recently, various lightweight methods for using Convolutional Neural Network(CNN) models in mobile devices have emerged. Weight quantization, which lowers bit precision of weights, is a lightweight method that enables a model to be used through integer calculation in a mobile environment where GPU acceleration is unable. Weight quantization has already been used in various models as a lightweight method to reduce computational complexity and model size with a small loss of accuracy. Considering the size of memory and computing speed as well as the storage size of the device and the limited network environment, this paper proposes a method of compressing integer weights after quantization using a video codec as a method. To verify the performance of the proposed method, experiments were conducted on VGG16, Resnet50, and Resnet18 models trained with ImageNet and Places365 datasets. As a result, loss of accuracy less than 2% and high compression efficiency were achieved in various models. In addition, as a result of comparison with similar compression methods, it was verified that the compression efficiency was more than doubled.

Research on Driving Pattern Analysis Techniques Using Contrastive Learning Methods (대조학습 방법을 이용한 주행패턴 분석 기법 연구)

  • Hoe Jun Jeong;Seung Ha Kim;Joon Hee Kim;Jang Woo Kwon
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.23 no.1
    • /
    • pp.182-196
    • /
    • 2024
  • This study introduces driving pattern analysis and change detection methods using smartphone sensors, based on contrastive learning. These methods characterize driving patterns without labeled data, allowing accurate classification with minimal labeling. In addition, they are robust to domain changes, such as different vehicle types. The study also examined the applicability of these methods to smartphones by comparing them with six lightweight deep-learning models. This comparison supported the development of smartphone-based driving pattern analysis and assistance systems, utilizing smartphone sensors and contrastive learning to enhance driving safety and efficiency while reducing the need for extensive labeled data. This research offers a promising avenue for addressing contemporary transportation challenges and advancing intelligent transportation systems.

Concurrent Detection for Vehicles and Lanes Using Light-Weight Model of Multi-Task CNN (멀티 테스크 CNN의 경량화 모델을 이용한 차량 및 차선의 동시 검출)

  • Shin, Hyeon-Sik;Kim, Hyung-Won;Hong, Sang-Wook
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.3
    • /
    • pp.367-373
    • /
    • 2022
  • As deep learning-based autonomous driving technology develops, artificial intelligence models for various purposes have been studied. Based on these studies, several models were used simultaneously to develop autonomous driving systems. It can occur by increasing hardware resource consumption. We propose a multi-tasks model using a shared backbone to solve this problem. This can solve the increase in the number of backbones for using AI models. As a result, in the proposed lightweight model, the model parameters could be reduced by more than 50% compared to the existing model, and the speed could be improved. In addition, each lane can be classified through lane detection using the instance segmentation method. However, further research is needed on the decrease in accuracy compared to the existing model.

Classification Method based on Graph Neural Network Model for Diagnosing IoT Device Fault (사물인터넷 기기 고장 진단을 위한 그래프 신경망 모델 기반 분류 방법)

  • Kim, Jin-Young;Seon, Joonho;Yoon, Sung-Hun
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.22 no.3
    • /
    • pp.9-14
    • /
    • 2022
  • In the IoT(internet of things) where various devices can be connected, failure of essential devices may lead to a lot of economic and life losses. For reducing the losses, fault diagnosis techniques have been considered an essential part of IoT. In this paper, the method based on a graph neural network is proposed for determining fault and classifying types by extracting features from vibration data of systems. For training of the deep learning model, fault dataset are used as input data obtained from the CWRU(case western reserve university). To validate the classification performance of the proposed model, a conventional CNN(convolutional neural networks)-based fault classification model is compared with the proposed model. From the simulation results, it was confirmed that the classification performance of the proposed model outweighed the conventional model by up to 5% in the unevenly distributed data. The classification runtime can be improved by lightweight the proposed model in future works.