Convolutional Neural Networks
ResNeXt
Introduced by Xie et al. in Aggregated Residual Transformations for Deep Neural NetworksA ResNeXt repeats a building block that aggregates a set of transformations with the same topology. Compared to a ResNet, it exposes a new dimension, cardinality (the size of the set of transformations) $C$, as an essential factor in addition to the dimensions of 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 | 37 | 15.81% |
| Image Classification | 28 | 11.97% |
| Semantic Segmentation | 22 | 9.40% |
| General Classification | 19 | 8.12% |
| Instance Segmentation | 15 | 6.41% |
| Action Recognition | 7 | 2.99% |
| Panoptic Segmentation | 6 | 2.56% |
| Pose Estimation | 4 | 1.71% |
| Real-Time Object Detection | 4 | 1.71% |
1x1 Convolution
Batch Normalization
Convolution
Global Average Pooling
Grouped Convolution
Kaiming Initialization
ReLU
Residual Connection
ResNeXt Block
