A Summary on Few-Shot Object Detection via Transfer Learning

Convolutional neural networks usually require a lot of annotated data for object detection. To avoid the need to acquire and annotate these huge amounts of data, few-shot object detection aims to learn from few object instances of new categories in the target domain. This paper provides a summary on some of the most recent state-of-the-art few shot object detection methods based on transfer learning. Then compare their results on two most common datasets for the task of object detection.

کلیدواژه ها:

Object Detection ، Few Shot Object Detection ، Transfer Learning ، Meta Learning