Skip Connection Blocks
One-Shot Aggregation
Introduced by Lee et al. in An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object DetectionOne-Shot Aggregation is an image model block that is an alternative to Dense Blocks, by aggregating intermediate features. It is proposed as part of the VoVNet architecture. Each convolution layer is connected by two-way connection. One way is connected to the subsequent layer to produce the feature with a larger receptive field while the other way is aggregated only once into the final output feature map. The difference with DenseNet is that the output of each layer is not routed to all subsequent intermediate layers which makes the input size of intermediate layers constant.
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 | 4 | 12.90% |
| Semantic Segmentation | 4 | 12.90% |
| Real-Time Object Detection | 3 | 9.68% |
| Instance Segmentation | 2 | 6.45% |
| Federated Learning | 1 | 3.23% |
| 2D Object Detection | 1 | 3.23% |
| Medical Diagnosis | 1 | 3.23% |
| medical image detection | 1 | 3.23% |
| Medical Object Detection | 1 | 3.23% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
1x1 Convolution
|
Convolutions | |
Batch Normalization
|
Normalization | |
Concatenated Skip Connection
|
Skip Connections | |
Convolution
|
Convolutions |
