본문 바로가기

convolutional neural network12

비전 딥러닝 특강 - 4-1. 비전 딥러닝 설계 / 합성곱 신경망이란? 2023. 4. 2.
[Review] Minaee et al., 2021, Image Segmentation Using Deep Learning: A Survey (* 작성 중; ~2022.11.04) # 세줄 요약 # 이미지 분할(Image segmentation)은 컴퓨터 비전(computer vision)과 영상처리(image processing)에서 가장 중요한 업무 중의 하나로 장면 이해, 의료 영상 분석, 로봇 인식, 비디오 감시, 증강 현실, 이미지 압축 등의 다양한 분야에서 여러 분할 알고리즘들이 선행 연구 문헌에서 발견된다. 저자들은 최근 문헌들을 뒤져서 픽셀 단위에서 작동하는 semantic and instance segmentation 합성곱 신경망, 인코더-디코더 구조, 다양한 스케일에서 피라미드 구조 접근법, 순환 신경망, 시각적 집중 모델(visual attention models), 적대적 생성 신경망(generative models i.. 2022. 10. 21.
[U-Net] Ronneberger et al., 2015, U-Net: Convolutional Networks for Biomedical Image Segmentation. # Three-line Summary # We present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. Using the network trained on transmitted light microscopy images, we won the ISBI cell trac.. 2022. 8. 11.
[MobileNet] Howard et al., 2017, MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications # 세줄 요약 # MobileNets are based on a streamlined architecture that uses depthwise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet clas.. 2022. 3. 21.
[DenseNet] Huang et al., 2017, Densely Connected Convolutional Networks # 세줄 요약 # We introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. For each layer, the feature-maps of all preceding layers are used as inputs, and their own feature-maps are used as inputs into all subsequent layers. DenseNet has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feat.. 2022. 3. 13.
Wang et al., 2019, Pathology Image Analysis Using Segmentation Deep Learning Algorithms. # 세줄 요약 # With the rapid development of image scanning techniques and visualization software, whole slide imaging (WSI) is becoming a routine diagnostic method. Deep learning-based pathology image segmentation has become an important tool in WSI analysis because that algorithms such as fully convolutional networks stand out for their accuracy, computational efficiency, and generalizability. In t.. 2021. 12. 20.
Kim et al., 2020, Active learning for accuracy enhancement of semantic segmentation with CNN-corrected label curations: Evaluation on kidney segmentation in abdominal CT # 세줄 요약 # Recent advances in fully convolutional networks have enabled automatic segmentation, however, high labeling efforts and difficulty in acquiring sufficient and high-quality training data is still a challenge. In this study, a cascaded 3D U-Net with active learning to 3 stages: first, training small dataset with manual labeling ground truth, second, training previous dataset and newly ad.. 2021. 8. 16.
Shim et al., 2020, Automated rotator cuff tear classification using 3D convolutional neural network # 세줄 요약 # Rotator cuff tear (RCT) is one of the most common shoulder injuries. When diagnosing RCT, skilled orthopedists visually interpret magnetic resonance imaging (MRI) scan data. MRI data from 2,124 patients were used to train and test the VRN-based 3D CNN to classify RCT into five classes (None, Partial, Small, Medium, Large-to-Massive). The VRN-based 3D CNN outperformed orthopedists speci.. 2021. 8. 8.
케라스 창시자에게 배우는 딥러닝 - 5. 컴퓨터 비전을 위한 딥러닝 # 세줄 요약 # 합성곱 신경망(Convolutional Neural Network)은 합성곱층(Convolutional layer)와 풀링층(Pooling layer)로 이루어진 신경망을 의미하며, 시각적인 문제(Computer Vision)를 다루는데 가장 강력한 툴이다. 적은 이미지 데이터셋을 가지고 있을때 효과적인 방법은 사전 훈련된 네트워크(pretrained network)를 이용하여 특성 추출(feature extraction) 또는 미세 조정(fine tunning) 방법을 사용하는 것이다. 일반적인 딥러닝 모델이 블랙박스(학습 과정을 사람이 이해하기 어려움)인 것에 반해 시각적인 패턴을 학습하는 합성곱 신경망은 중간층의 출력(feature map), 필터(filter)와 클래스 활성화에 .. 2020. 11. 16.
Choi & Jin, 2018, Predicting Cognitive Decline with Deep Learning of Brain Metabolism and Amyloid Imaging # 세줄요약 # 인간에게 치명적인 인지기능 장애를 가져오는 알츠하이머 질병을 진단하기 위하여 CNN 기반의 진단 알고리즘을 개발하였으며, 먼저 AD(Alzheimer Disease)와 NC(Normal Control)을 분류하는 모델을 먼저 학습시킨 후, MCI(Mild Cognitive Inpairment) 환자들이 치매로 전환(Converter or Nonconverter)되는지를 학습시켰다. 학습 데이터로는 ADNI 오픈 데이터셋의 FDG와 AV-45 PET 영상들을 사용하였으며, 이때 딥러닝은 특성 추출을 자동으로 하기에 Spatial Normalization 같이 뇌영상에서 전통적으로 사용되던 영상처리 기법들은 적용하지 않았다. 학습 결과 AD vs NC 환자 분류와 MCI 환자들 중 AD 환자.. 2020. 2. 24.

티스토리툴바