Convolutional Neural Networks
SNet
Introduced by Qin et al. in ThunderNet: Towards Real-time Generic Object DetectionSNet is a convolutional neural network architecture and object detection backbone used for the ThunderNet two-stage object detector. SNet uses ShuffleNetV2 basic blocks but replaces all 3×3 depthwise convolutions with 5×5 depthwise convolutions.
Source: ThunderNet: Towards Real-time Generic Object Detection
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 3 | 23.08% |
| Mixed Reality | 2 | 15.38% |
| Object Detection | 2 | 15.38% |
| Image Segmentation | 1 | 7.69% |
| Medical Image Segmentation | 1 | 7.69% |
| Image Generation | 1 | 7.69% |
| Image Restoration | 1 | 7.69% |
| Rain Removal | 1 | 7.69% |
| Single Image Deraining | 1 | 7.69% |
1x1 Convolution
Dense Connections
Global Average Pooling
Max Pooling
ShuffleNet V2 Block
Softmax
