Degridding
Hierarchical Feature Fusion
Introduced by Mehta et al. in ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic SegmentationHierarchical Feature Fusion (HFF) is a feature fusion method employed in ESP and EESP image model blocks for degridding. In the ESP module, concatenating the outputs of dilated convolutions gives the ESP module a large effective receptive field, but it introduces unwanted checkerboard or gridding artifacts. To address the gridding artifact in ESP, the feature maps obtained using kernels of different dilation rates are hierarchically added before concatenating them (HFF). This solution is simple and effective and does not increase the complexity of the ESP module.
Source: ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Speech Recognition | 13 | 10.92% |
| Automatic Speech Recognition (ASR) | 9 | 7.56% |
| Semantic Segmentation | 6 | 5.04% |
| Object Detection | 4 | 3.36% |
| Reinforcement Learning | 4 | 3.36% |
| Decoder | 3 | 2.52% |
| Language Modeling | 3 | 2.52% |
| Language Modelling | 3 | 2.52% |
| Reinforcement Learning (RL) | 3 | 2.52% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
