Object Detection Models
Region-based Fully Convolutional Network
Introduced by Dai et al. in R-FCN: Object Detection via Region-based Fully Convolutional NetworksRegion-based Fully Convolutional Networks, or R-FCNs, are a type of region-based object detector. In contrast to previous region-based object detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, R-FCN is fully convolutional with almost all computation shared on the entire image.
To achieve this, R-FCN utilises position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection.
Source: R-FCN: Object Detection via Region-based Fully Convolutional Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 24 | 39.34% |
| General Classification | 3 | 4.92% |
| Object Recognition | 2 | 3.28% |
| Traffic Sign Detection | 2 | 3.28% |
| Real-Time Object Detection | 2 | 3.28% |
| Classification | 2 | 3.28% |
| Object Tracking | 1 | 1.64% |
| Template Matching | 1 | 1.64% |
| Video Object Detection | 1 | 1.64% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Convolution
|
Convolutions | |
Position-Sensitive RoI Pooling
|
RoI Feature Extractors |
