Skip Connection Blocks
ResNeXt Block
Introduced by Xie et al. in Aggregated Residual Transformations for Deep Neural NetworksA ResNeXt Block is a type of residual block used as part of the ResNeXt CNN architecture. It uses a "split-transform-merge" strategy (branched paths within a single module) similar to an Inception module, i.e. it aggregates a set of transformations. Compared to a Residual Block, it exposes a new dimension, cardinality (size of set of transformations) $C$, as an essential factor in addition to depth and width.
Formally, a set of aggregated transformations can be represented as: $\mathcal{F}(x)=\sum_{i=1}^{C}\mathcal{T}_i(x)$, where $\mathcal{T}_i(x)$ can be an arbitrary function. Analogous to a simple neuron, $\mathcal{T}_i$ should project $x$ into an (optionally low-dimensional) embedding and then transform it.
Source: Aggregated Residual Transformations for Deep Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 38 | 14.29% |
| Image Classification | 28 | 10.53% |
| Semantic Segmentation | 23 | 8.65% |
| General Classification | 19 | 7.14% |
| Instance Segmentation | 15 | 5.64% |
| Classification | 8 | 3.01% |
| Action Recognition | 7 | 2.63% |
| Panoptic Segmentation | 6 | 2.26% |
| Real-Time Object Detection | 5 | 1.88% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
1x1 Convolution
|
Convolutions | |
Batch Normalization
|
Normalization | |
Convolution
|
Convolutions | |
Grouped Convolution
|
Convolutions | |
ReLU
|
Activation Functions | |
Residual Connection
|
Skip Connections |
