Convolutional Neural Networks
VoVNet
Introduced by Lee et al. in An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object DetectionVoVNet is a convolutional neural network that seeks to make DenseNet more efficient by concatenating all features only once in the last feature map, which makes input size constant and enables enlarging new output channel. In the Figure to the right, $F$ represents a convolution layer and $\otimes$ indicates concatenation.
Source: An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 2 | 15.38% |
| Real-Time Object Detection | 2 | 15.38% |
| Semantic Segmentation | 2 | 15.38% |
| 3D Object Detection | 1 | 7.69% |
| Defect Detection | 1 | 7.69% |
| Instance Segmentation | 1 | 7.69% |
| Panoptic Segmentation | 1 | 7.69% |
| Real-time Instance Segmentation | 1 | 7.69% |
| Semi-Supervised Instance Segmentation | 1 | 7.69% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Convolution
|
Convolutions | |
Max Pooling
|
Pooling Operations | |
One-Shot Aggregation
|
Skip Connection Blocks |
