A 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 NetworkPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 74 | 12.07% |
Image Classification | 53 | 8.65% |
Semantic Segmentation | 41 | 6.69% |
Self-Supervised Learning | 20 | 3.26% |
Quantization | 14 | 2.28% |
Knowledge Distillation | 12 | 1.96% |
Instance Segmentation | 10 | 1.63% |
Image Generation | 10 | 1.63% |
Autonomous Driving | 9 | 1.47% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |