Object Detection Models
Fast R-CNN
Introduced by Girshick in Fast R-CNNFast R-CNN is an object detection model that improves in its predecessor R-CNN in a number of ways. Instead of extracting CNN features independently for each region of interest, Fast R-CNN aggregates them into a single forward pass over the image; i.e. regions of interest from the same image share computation and memory in the forward and backward passes.
Source: Fast R-CNN
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 23 | 33.82% |
| General Classification | 4 | 5.88% |
| Classification | 3 | 4.41% |
| Real-Time Object Detection | 3 | 4.41% |
| Object Recognition | 3 | 4.41% |
| Weakly Supervised Object Detection | 2 | 2.94% |
| Autonomous Driving | 2 | 2.94% |
| Autonomous Vehicles | 2 | 2.94% |
| Pedestrian Detection | 2 | 2.94% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Convolution
|
Convolutions | |
RoIPool
|
RoI Feature Extractors | |
Softmax
|
Output Functions |
