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 | 62 | 8.86% |
Semantic Segmentation | 42 | 6.00% |
Image Classification | 36 | 5.14% |
Classification | 29 | 4.14% |
Self-Supervised Learning | 17 | 2.43% |
Image Segmentation | 16 | 2.29% |
Quantization | 14 | 2.00% |
Reinforcement Learning (RL) | 12 | 1.71% |
Autonomous Driving | 9 | 1.29% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |