• 제목/요약/키워드: Pre-trained Model

검색결과 286건 처리시간 0.019초

Novel Category Discovery in Plant Species and Disease Identification through Knowledge Distillation

  • Jiuqing Dong;Alvaro Fuentes;Mun Haeng Lee;Taehyun Kim;Sook Yoon;Dong Sun Park
    • 스마트미디어저널
    • /
    • 제13권7호
    • /
    • pp.36-44
    • /
    • 2024
  • Identifying plant species and diseases is crucial for maintaining biodiversity and achieving optimal crop yields, making it a topic of significant practical importance. Recent studies have extended plant disease recognition from traditional closed-set scenarios to open-set environments, where the goal is to reject samples that do not belong to known categories. However, in open-world tasks, it is essential not only to define unknown samples as "unknown" but also to classify them further. This task assumes that images and labels of known categories are available and that samples of unknown categories can be accessed. The model classifies unknown samples by learning the prior knowledge of known categories. To the best of our knowledge, there is no existing research on this topic in plant-related recognition tasks. To address this gap, this paper utilizes knowledge distillation to model the category space relationships between known and unknown categories. Specifically, we identify similarities between different species or diseases. By leveraging a fine-tuned model on known categories, we generate pseudo-labels for unknown categories. Additionally, we enhance the baseline method's performance by using a larger pre-trained model, dino-v2. We evaluate the effectiveness of our method on the large plant specimen dataset Herbarium 19 and the disease dataset Plant Village. Notably, our method outperforms the baseline by 1% to 20% in terms of accuracy for novel category classification. We believe this study will contribute to the community.

반려견 자동 품종 분류를 위한 전이학습 효과 분석 (Analysis of Transfer Learning Effect for Automatic Dog Breed Classification)

  • 이동수;박구만
    • 방송공학회논문지
    • /
    • 제27권1호
    • /
    • pp.133-145
    • /
    • 2022
  • 국내에서 지속적으로 증가하는 반려견 인구 및 산업 규모에 비해 이와 관련한 데이터의 체계적인 분석이나 품종 분류 방법 연구 등은 매우 부족한 실정이다. 본 논문에서는 국내에서 양육되는 반려견의 주요 14개 품종에 대해 딥러닝 기술을 이용한 자동 품종 분류 방법을 수행하였다. 이를 위해 먼저 딥러닝 학습을 위한 반려견 이미지를 수집하고 데이터셋을 구축하였으며, VGG-16 및 Resnet-34를 백본 네트워크로 사용하는 전이학습을 각각 수행하여 품종 분류 알고리즘을 만들었다. 반려견 이미지에 대한 두 모델의 전이학습 효과를 확인하기 위해, Pre-trained 가중치를 사용한 것과 가중치를 업데이트하는 실험을 수행하여 비교하였으며, VGG-16 기반으로 fine tuning을 수행했을 때, 최종 모델에서 Top 1 정확도는 약 89%, Top 3 정확도는 약 94%의 정확도 성능을 각각 얻을수 있었다. 본 논문에서 제안하는 국내의 주요 반려견 품종 분류 방법 및 데이터 구축은 동물보호센터에서의 유기·유실견 품종 구분이나 사료 산업체에서의 활용 등 여러가지 응용 목적으로도 활용될 수 있는 가능성을 가지고 있다.

Users' Attachment Styles and ChatGPT Interaction: Revealing Insights into User Experiences

  • I-Tsen Hsieh;Chang-Hoon Oh
    • 한국컴퓨터정보학회논문지
    • /
    • 제29권3호
    • /
    • pp.21-41
    • /
    • 2024
  • 본 연구는 OpenAI가 개발한 고급 언어 모델인 ChatGPT (Chat Generative Pre-trained Transformer)와 사용자의 애착 유형 간의 관계를 탐구한다. 인공지능(AI)이 점차 일상생활에 통합되면서, 다양한 애착 유형을 가진 개인들이 AI 챗봇과 상호 작용하는 방식을 이해하는 것은 특정 사용자 요구를 충족하고 사용자와 가장 이상적인 방식으로 상호 작용하는 더 나은 사용자 경험을 구축하기 위해 중요하다. 심리학의 애착 이론을 기반으로 한 이 연구에서는 애착 유형이 ChatGPT와 상호 작용에 미치는 영향을 탐구하여 인간과 AI 간의 상호 작용에 대한 이해에서 중요한 공백을 메우고 있다. 예상과는 달리, 애착 유형은 ChatGPT 사용에 유의미한 영향을 미치지 않았다. 애착 유형에 관계없이 중요한 정보를 전달하는 ChatGPT를 완전히 신뢰하는 것을 주저했으며, AI 시스템의 신뢰 문제를 해결해야 할 필요성을 강조한다. 단, 본 연구는 사용자와 ChatGPT 간 독특한 상호 작용에 중점을 두어, 애착 유형이 이러한 상호 작용에 미치는 영향을 해명하여 AI 챗봇의 개인화된 사용자 경험을 개발하는 데에 도움이 되고자 한다. 또, 본 연구는 Perceived Partner Responsiveness Scale의 도입은 사용자가 ChatGPT의 역할에 대한 인식을 평가하는 유용한 도구로 기능하며, AI의 인격화에 대한 관점을 제시한다. 본 연구는 인간과 AI 간의 관계에 대한 넓은 토론에 기여하며, 사용자 중심의 미래를 위해 AI 시스템에 감정 지능을 통합하는 중요성을 강조한다.

전문어의 범용 공간 매핑을 위한 비선형 벡터 정렬 방법론 (Nonlinear Vector Alignment Methodology for Mapping Domain-Specific Terminology into General Space)

  • 김준우;윤병호;김남규
    • 지능정보연구
    • /
    • 제28권2호
    • /
    • pp.127-146
    • /
    • 2022
  • 최근 워드 임베딩이 딥러닝 기반 자연어 처리를 다루는 다양한 업무에서 우수한 성능을 나타내면서, 단어, 문장, 그리고 문서 임베딩의 고도화 및 활용에 대한 연구가 활발하게 이루어지고 있다. 예를 들어 교차 언어 전이는 서로 다른 언어 간의 의미적 교환을 가능하게 하는 분야로, 임베딩 모델의 발전과 동시에 성장하고 있다. 또한 핵심 기술인 벡터 정렬(Vector Alignment)은 임베딩 기반 다양한 분석에 적용될 수 있다는 기대에 힘입어 학계의 관심이 더욱 높아지고 있다. 특히 벡터 정렬은 최근 수요가 높아지고 있는 분야간 매핑, 즉 대용량의 범용 문서로 학습된 사전학습 언어모델의 공간에 R&D, 의료, 법률 등 전문 분야의 어휘를 매핑하거나 이들 전문 분야간의 어휘를 매핑하기 위한 실마리를 제공할 수 있을 것으로 기대된다. 하지만 학계에서 주로 연구되어 온 선형 기반 벡터 정렬은 기본적으로 통계적 선형성을 가정하기 때문에, 본질적으로 상이한 형태의 벡터 공간을 기하학적으로 유사한 것으로 간주하는 가정으로 인해 정렬 과정에서 필연적인 왜곡을 야기한다는 한계를 갖는다. 본 연구에서는 이러한 한계를 극복하기 위해 데이터의 비선형성을 효과적으로 학습하는 딥러닝 기반 벡터 정렬 방법론을 제안한다. 제안 방법론은 서로 다른 공간에서 벡터로 표현된 전문어 임베딩을 범용어 임베딩 공간에 정렬하는 스킵연결 오토인코더와 회귀 모델의 순차별 학습으로 구성되며, 학습된 두 모델의 추론을 통해 전문 어휘를 범용어 공간에 정렬할 수 있다. 제안 방법론의 성능을 검증하기 위해 2011년부터 2020년까지 수행된 국가 R&D 과제 중 '보건의료' 분야의 문서 총 77,578건에 대한 실험을 수행한 결과, 제안 방법론이 기존의 선형 벡터 정렬에 비해 코사인 유사도 측면에서 우수한 성능을 나타냄을 확인하였다.

Plant Disease Identification using Deep Neural Networks

  • Mukherjee, Subham;Kumar, Pradeep;Saini, Rajkumar;Roy, Partha Pratim;Dogra, Debi Prosad;Kim, Byung-Gyu
    • Journal of Multimedia Information System
    • /
    • 제4권4호
    • /
    • pp.233-238
    • /
    • 2017
  • Automatic identification of disease in plants from their leaves is one of the most challenging task to researchers. Diseases among plants degrade their performance and results into a huge reduction of agricultural products. Therefore, early and accurate diagnosis of such disease is of the utmost importance. The advancement in deep Convolutional Neural Network (CNN) has change the way of processing images as compared to traditional image processing techniques. Deep learning architectures are composed of multiple processing layers that learn the representations of data with multiple levels of abstraction. Therefore, proved highly effective in comparison to many state-of-the-art works. In this paper, we present a plant disease identification methodology from their leaves using deep CNNs. For this, we have adopted GoogLeNet that is considered a powerful architecture of deep learning to identify the disease types. Transfer learning has been used to fine tune the pre-trained model. An accuracy of 85.04% has been recorded in the identification of four disease class in Apple plant leaves. Finally, a comparison with other models has been performed to show the effectiveness of the approach.

Sketch Recognition Using LSTM with Attention Mechanism and Minimum Cost Flow Algorithm

  • Nguyen-Xuan, Bac;Lee, Guee-Sang
    • International Journal of Contents
    • /
    • 제15권4호
    • /
    • pp.8-15
    • /
    • 2019
  • This paper presents a solution of the 'Quick, Draw! Doodle Recognition Challenge' hosted by Google. Doodles are drawings comprised of concrete representational meaning or abstract lines creatively expressed by individuals. In this challenge, a doodle is presented as a sequence of sketches. From the view of at the sketch level, to learn the pattern of strokes representing a doodle, we propose a sequential model stacked with multiple convolution layers and Long Short-Term Memory (LSTM) cells following the attention mechanism [15]. From the view at the image level, we use multiple models pre-trained on ImageNet to recognize the doodle. Finally, an ensemble and a post-processing method using the minimum cost flow algorithm are introduced to combine multiple models in achieving better results. In this challenge, our solutions garnered 11th place among 1,316 teams. Our performance was 0.95037 MAP@3, only 0.4% lower than the winner. It demonstrates that our method is very competitive. The source code for this competition is published at: https://github.com/ngxbac/Kaggle-QuickDraw.

Robust Deep Age Estimation Method Using Artificially Generated Image Set

  • Jang, Jaeyoon;Jeon, Seung-Hyuk;Kim, Jaehong;Yoon, Hosub
    • ETRI Journal
    • /
    • 제39권5호
    • /
    • pp.643-651
    • /
    • 2017
  • Human age estimation is one of the key factors in the field of Human-Robot Interaction/Human-Computer Interaction (HRI/HCI). Owing to the development of deep-learning technologies, age recognition has recently been attempted. In general, however, deep learning techniques require a large-scale database, and for age learning with variations, a conventional database is insufficient. For this reason, we propose an age estimation method using artificially generated data. Image data are artificially generated through 3D information, thus solving the problem of shortage of training data, and helping with the training of the deep-learning technique. Augmentation using 3D has advantages over 2D because it creates new images with more information. We use a deep architecture as a pre-trained model, and improve the estimation capacity using artificially augmented training images. The deep architecture can outperform traditional estimation methods, and the improved method showed increased reliability. We have achieved state-of-the-art performance using the proposed method in the Morph-II dataset and have proven that the proposed method can be used effectively using the Adience dataset.

Multi-class Classification of Histopathology Images using Fine-Tuning Techniques of Transfer Learning

  • Ikromjanov, Kobiljon;Bhattacharjee, Subrata;Hwang, Yeong-Byn;Kim, Hee-Cheol;Choi, Heung-Kook
    • 한국멀티미디어학회논문지
    • /
    • 제24권7호
    • /
    • pp.849-859
    • /
    • 2021
  • Prostate cancer (PCa) is a fatal disease that occurs in men. In general, PCa cells are found in the prostate gland. Early diagnosis is the key to prevent the spreading of cancers to other parts of the body. In this case, deep learning-based systems can detect and distinguish histological patterns in microscopy images. The histological grades used for the analysis were benign, grade 3, grade 4, and grade 5. In this study, we attempt to use transfer learning and fine-tuning methods as well as different model architectures to develop and compare the models. We implemented MobileNet, ResNet50, and DenseNet121 models and used three different strategies of freezing layers techniques of fine-tuning, to get various pre-trained weights to improve accuracy. Finally, transfer learning using MobileNet with the half-layer frozen showed the best results among the nine models, and 90% accuracy was obtained on the test data set.

An Automatic Strabismus Screening Method with Corneal Light Reflex based on Image Processing

  • Huang, Xi-Lang;Kim, Chang Zoo;Choi, Seon Han
    • 한국멀티미디어학회논문지
    • /
    • 제24권5호
    • /
    • pp.642-650
    • /
    • 2021
  • Strabismus is one of the most common disease that might be associated with vision impairment. Especially in infants and children, it is critical to detect strabismus at an early age because uncorrected strabismus may go on to develop amblyopia. To this end, ophthalmologists usually perform the Hirschberg test, which observes corneal light reflex (CLR) to determine the presence and type of strabismus. However, this test is usually done manually in a hospital, which might be difficult for patients who live in a remote area with poor medical access. To address this issue, we propose an automatic strabismus screening method that calculates the CLR ratio to determine the presence of strabismus based on image processing. In particular, the method first employs a pre-trained face detection model and a 68 facial landmarks detector to extract the eye region image. The data points located in the limbus are then collected, and the least square method is applied to obtain the center coordinates of the iris. Finally, the coordinate of the reflective light point center within the iris is extracted and used to calculate the CLR ratio with the coordinate of iris edges. Experimental results with several images demonstrate that the proposed method can be a promising solution to provide strabismus screening for patients who cannot visit hospitals.

디지털 개인비서 동향과 미래 (Trends and Future of Digital Personal Assistant)

  • 권오욱;이기영;이요한;노윤형;조민수;황금하;임수종;최승권;김영길
    • 전자통신동향분석
    • /
    • 제36권1호
    • /
    • pp.1-11
    • /
    • 2021
  • In this study, we introduce trends in and the future of digital personal assistants. Recently, digital personal assistants have begun to handle many tasks like humans by communicating with users in human language on smart devices such as smart phones, smart speakers, and smart cars. Their capabilities range from simple voice commands and chitchat to complex tasks such as device control, reservation, ordering, and scheduling. The digital personal assistants of the future will certainly speak like a person, have a person-like personality, see, hear, and analyze situations like a person, and become more human. Dialogue processing technology that makes them more human-like has developed into an end-to-end learning model based on deep neural networks in recent years. In addition, language models pre-trained from a large corpus make dialogue processing more natural and better understood. Advances in artificial intelligence such as dialogue processing technology will enable digital personal assistants to serve with more familiar and better performance in various areas.