Skip to content

Commit bff5e57

Browse files
authored
Update README.md
1 parent c56a4c0 commit bff5e57

File tree

1 file changed

+6
-0
lines changed

1 file changed

+6
-0
lines changed

README.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,8 @@ Deep Learning 기반의 모델링으로 Object Detection 문제를 효과적으
1010
![Summary SlideShare #1](/object-detection-1.png?raw=true "Summary")
1111

1212

13+
14+
1315
### R-CNN 이전의 모델
1416

1517
![Summary : Before R-CNN](/object-detection-2.png?raw=true "Before R-CNN")
@@ -19,6 +21,8 @@ Deep Learning 기반의 모델링으로 Object Detection 문제를 효과적으
1921
* [OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks](https://arxiv.org/abs/1312.6229)
2022
* [Deep Neural Networks for Object Detection](https://pdfs.semanticscholar.org/713f/73ce5c3013d9fb796c21b981dc6629af0bd5.pdf)
2123

24+
25+
2226
### R-CNN 류의 모델 : R-CNN의 모듈들을 개선했거나 유사 구조의 Detection Pipeline을 사용
2327

2428
![Summary : R-CNN](/object-detection-3.png?raw=true "R-CNN")
@@ -35,6 +39,8 @@ Deep Learning 기반의 모델링으로 Object Detection 문제를 효과적으
3539
* [Faster R-CNN +++](https://arxiv.org/abs/1512.03385)
3640
* [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://arxiv.org/abs/1605.06409) : Faster R-CNN을 Fully Convolutional 하게 변경.
3741

42+
43+
3844
### Single Shot Detector : 1번의 Neural Network Forwarding으로 여러 클래스의 여러 물체를 동시 검출하는 Pipeline을 사용
3945

4046
![Summary : Single Shot Detector](/object-detection-4.png?raw=true "Single Shot detector 1")

0 commit comments

Comments
 (0)