Course Study with CSC321
[2021.05.29]
Topic
: Lecture 13.6: Object Detection YOLO v1 (Chanju, James, Chloe)
Notes
:
- https://drive.google.com/file/d/1WSqIcKwjyRALc4T3v0L3sBim5XuiSjkV/view?usp=sharing [Chanju]
- https://drive.google.com/file/d/18ITsaPJeyCBJVEUfjxaFFfgXxoiXjxk6/view?usp=sharing [James]
- https://drive.google.com/file/d/1-61pnmfN_boV-Xgif2br8nUWN2hEh6Ge/view?usp=sharing [Chloe]
Links
:
- https://arxiv.org/pdf/1506.02640.pdf (원 논문)
- https://jonathan-hui.medium.com/real-time-object-detection-with-yolo-yolov2-28b1b93e2088 (how output of final fc layer is tensor, not vector? => reshape, EN)
- https://curt-park.github.io/2017-03-26/yolo/ (computation flow, KR)
- https://kevin970401.github.io/cnn/2019/08/19/detection.html (yolo limits, KR)
Covered through study
- What’s improved? (or suggested?)
- object-detection as single-regression problem
- three benefits over traditional models
- Architecture & Computation flow
- network design
- how raw image pass-through model (checking in/out of every layer)
- Train & Inference
- understanding each term of sum-squared error
- using
λcoord
,λnoobj
parameters- Limits & Comparison to other previous models
- limits : spatial constraint, small-object problem, coarse features, loss-balance
- comparison :
DPM
,Deep MultiBox
,OverFeat
,MultiGrasp
제외
YOLO v1