DeepLearning Paper with Code

스터디 개요

  • 스터디 목표
    • 주요 딥러닝 논문을 보며 모델링을 할 때 어떻게 코드로 작성할 수 있는지를 학습
  • 스터디 방법
    • 매주 화요일에 모여 돌아가면서 그 주의 논문을 읽고 코드로 구현하고 와서 각자 맡은 파트를 스터디 원에게 설명

커리큘럼

  몇 주차   논문   발표자  
1주차 AlexNet - ImageNet Classification with Deep Convolutional Neural Network 조종호
1주차 GoogLeNet - Going Deeper with Convolutions 주미선
1주차 VGG - Very Deep Convolutional Networks for Large-Scale Image Recognition 박소민
2주차 ResNet - Deep Residual Learning for Image Recognition 조종호
3주차 UNet - U-Net: Convolutional Networks for Biomedical Image Segmentation 주미선
4주차 Inception v4 - Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning 박소민
5주차 DenseNet - Densely Connected Convolutional Networks 조종호
6주차 PreAct-ResNet - Identity Mappings in Deep Residual Networks 주미선
6주차 WRN- Wide Residual Networks 박소민
7주차 Residual Attention Network - Residual Attention Network for Image Classification 조종호
7주차 Xception - Xception: Deep Learning with Depthwise Separable Convolutions 주미선
8주차 SENet - Squeeze-and-Excitation Networks 박소민
8주차 MobileNet - MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications 조종호
9주차 CAM - Learning Deep Features for Discriminative Localization 주미선
9주차 EfficientNet - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks 박소민
10주차 Transformer - Attention Is All You Need 조종호
10주차 ViT - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 주미선