Object Detection Models
YOLOv3
Introduced by Redmon et al. in YOLOv3: An Incremental ImprovementYOLOv3 is a real-time, single-stage object detection model that builds on YOLOv2 with several improvements. Improvements include the use of a new backbone network, Darknet-53 that utilises residual connections, or in the words of the author, "those newfangled residual network stuff", as well as some improvements to the bounding box prediction step, and use of three different scales from which to extract features (similar to an FPN).
Source: YOLOv3: An Incremental Improvement
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 135 | 34.88% |
| Autonomous Driving | 17 | 4.39% |
| Real-Time Object Detection | 16 | 4.13% |
| Classification | 9 | 2.33% |
| Instance Segmentation | 7 | 1.81% |
| Pedestrian Detection | 6 | 1.55% |
| General Classification | 6 | 1.55% |
| Domain Adaptation | 5 | 1.29% |
| 2D Object Detection | 5 | 1.29% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Darknet-53
|
Convolutional Neural Networks | |
k-Means Clustering
|
Clustering | |
Logistic Regression
|
Generalized Linear Models |
