This folder contains sample scripts for one-shot learning.
One-shot learning is a type of machine learning where a model is trained on a single example of a class. This is useful for applications where the number of training examples is limited, such as in medical imaging. We provide two sample scripts for one-shot learning:
- Decoupled Faster R-CNN for Few-Shot Object Detection (DeFRCN)
- One-Stage One-Shot Object Detection by Matching Anchor Features (OS2D)
To run the juptyer notebooks, simply clone this repository and open the notebooks in your local environment. The notebooks can be run on Google Colab as well.