Course Study with CSC321

[2021.05.15]

Topic : Lecture 13.5: Object Detection Faster R-CNN part2 (Hayden, James)

Notes :

• https://drive.google.com/file/d/1UdzLboCNc1Sda4ns83RVS-ar-JhcVCZl/view?usp=sharing [Hayden]
• https://drive.google.com/file/d/1OhM4QieuKMh_Nlv5WkWv0iZ4-MXBV_IK/view?usp=sharing [James]

Links :

• https://herbwood.tistory.com/10 (Training RPN details, KR)
• https://www.telesens.co/2018/03/11/object-detection-and-classification-using-r-cnns/ (Training RPN details, EN)
• https://nuggy875.tistory.com/33 (Lreg term of RPN loss)
• https://ganghee-lee.tistory.com/37 (4-step alternating trainging of Faster R-CNN)
• https://ratsgo.github.io/deep%20learning/2017/04/05/CNNbackprop/ (remind of back-prop of maxpool layer)

스터디 RULE 수정

• 월/화 : 순서 변경이 필요한 팀원의 경우 화요일 저녁 전까지 다른 팀원에게 요청.
• 수: 해당 주 담당 팀원은 진행 정도 및 별도 준비가 필요한 부분을 James에게 전달.

Covered through study

Part 2

• Loss

  • what loss function is defined on RPN?

• Train

  • how to train RPN?

1. How RPN and Detector share feature maps?

• alternating training?

1. Implementation details

• 가능한 정도만
• used scales, anchor types

+ multibox approach (pyramids of filters)

+ understanding regression loss of RPN

​

​

Faster R-CNN part 2

​

​

​

​

​

​

​

​

​

​

​

​