Few Shot Object Detection via Knowledge Transfer

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes . In this paper, we introduce a few-shot object detection via knowledge transfer . Central to our method is prototypical knowledge transfer with an attached meta-learner . The prototypes reweight each RoI (Region-of-Interest) feature vector from a query image to remodels R-CNN predictor heads. To facilitate the remodeling process, we predict the prototypes under a graph structure, which propagates information of the correlated base categories to the novel categories with explicit guidance of prior knowledge that represents correlations among categories . Extensive experiments on the PASCAL VOC dataset verifies the effectiveness of the proposed method, including the PascAL Voc dataset. Extensive experiments verifies the proposed method. The researchers have published their findings on their findings. They are published in The New York Review of Science and Technology, published by MIT.

Links: PDF - Abstract

Code :

None

Keywords : knowledge - categories - object - detection - method -

Leave a Reply

Your email address will not be published. Required fields are marked *