Image Model Blocks
Efficient Spatial Pyramid
Introduced by Mehta et al. in ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic SegmentationAn Efficient Spatial Pyramid (ESP) is an image model block based on a factorization principle that decomposes a standard convolution into two steps: (1) point-wise convolutions and (2) spatial pyramid of dilated convolutions. The point-wise convolutions help in reducing the computation, while the spatial pyramid of dilated convolutions re-samples the feature maps to learn the representations from large effective receptive field. This allows for increased efficiency compared to another image blocks like ResNeXt blocks and Inception modules.
Source: ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Speech Recognition | 10 | 19.23% |
| Automatic Speech Recognition (ASR) | 8 | 15.38% |
| Semantic Segmentation | 5 | 9.62% |
| Language Modelling | 3 | 5.77% |
| Reinforcement Learning (RL) | 3 | 5.77% |
| Speech Separation | 2 | 3.85% |
| Real-Time Semantic Segmentation | 2 | 3.85% |
| Text Generation | 1 | 1.92% |
| Visual Commonsense Reasoning | 1 | 1.92% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Dilated Convolution
|
Convolutions | |
Hierarchical Feature Fusion
|
Degridding | |
Pointwise Convolution
|
Convolutions |
