스터디 진행 방식

논문 읽고 구현해오기 → 발표 → 코드리뷰 → 구현 업로드 → 논문 소감 공유

발표 순서

박준희(휴가) → 유창우 → 서병준 → Eddie → 김관영 → 이지환 → 유하린

발표자 (읽을 논문)

구현하기 → 아래 Github 레포에 업로드

https://github.com/MLB-Papers/paper-impl

읽어야하는 논문들

4강 CNN 논문

  1. LeCun et al., 1998. Gradient-based learning applied to document recognition]
  2. [Krizhevsky et al., 2012. ImageNet classification with deep convolutional neural networks]
  3. [He et al., 2015. Deep residual networks for image recognition]
    1. [Simonyan & Zisserman 2015. Very deep convolutional networks for large-scale image recognition]
  4. [Lin et al., 2013. Network in network]
  5. [Szegedy et al. 2014. Going deeper with convolutions]
  6. [Howard et al. 2017, MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications]
  7. [Sandler et al. 2019, MobileNetV2: Inverted Residuals and Linear Bottlenecks]
  8. [Tan and Le, 2019, EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks]
  9. [Sermanet et al., 2014, OverFeat: Integrated recognition, localization and detection using convolutional networks]
  10. [Redmon et al., 2015, You Only Look Once: Unified real-time object detection]
  11. [Girshik et. al, 2013, Rich feature hierarchies for accurate object detection and semantic segmentation]