Image Model Blocks
Inception-v3 Module
Introduced by Szegedy et al. in Rethinking the Inception Architecture for Computer VisionInception-v3 Module is an image block used in the Inception-v3 architecture. This architecture is used on the coarsest (8 × 8) grids to promote high dimensional representations.
Source: Rethinking the Inception Architecture for Computer Vision
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 16 | 12.40% |
| General Classification | 15 | 11.63% |
| Classification | 13 | 10.08% |
| Adversarial Attack | 5 | 3.88% |
| Quantization | 4 | 3.10% |
| Object Detection | 3 | 2.33% |
| Image Captioning | 3 | 2.33% |
| Semantic Segmentation | 3 | 2.33% |
| Management | 3 | 2.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
1x1 Convolution
|
Convolutions | |
Average Pooling
|
Pooling Operations | |
Convolution
|
Convolutions |
