Convolutions
1x1 Convolution
Introduced by Lin et al. in Network In NetworkA 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction, efficient low dimensional embeddings, and applying non-linearity after convolutions. It maps an input pixel with all its channels to an output pixel which can be squeezed to a desired output depth. It can be viewed as an MLP looking at a particular pixel location.
Image Credit: http://deeplearning.ai
Source: Network In Network
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 81 | 12.14% |
| Image Classification | 57 | 8.55% |
| Semantic Segmentation | 40 | 6.00% |
| General Classification | 39 | 5.85% |
| Instance Segmentation | 20 | 3.00% |
| Quantization | 14 | 2.10% |
| Self-Supervised Learning | 12 | 1.80% |
| Autonomous Driving | 9 | 1.35% |
| Domain Adaptation | 9 | 1.35% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |