Few-Shot Object Detection via Knowledge Transfer

Geonuk Kim, Hong Gyu Jung, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize. It exposes the practical weakness of the object detectors. On the other hand, human can easily master new reasoning rules with only a few demonstrations using previously learned knowledge. In this paper, we introduce a few-shot object detection via knowledge transfer, which aims to detect objects from a few training examples. Central to our method is prototypical knowledge transfer with an attached meta-learner. The meta-learner takes support set images that include the few examples of the novel categories and base categories, and predicts prototypes that represent each category as a vector. Then, 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.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3564-3569
Number of pages6
ISBN (Electronic)9781728185262
DOIs
Publication statusPublished - 2020 Oct 11
Event2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 - Toronto, Canada
Duration: 2020 Oct 112020 Oct 14

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume2020-October
ISSN (Print)1062-922X

Conference

Conference2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Country/TerritoryCanada
CityToronto
Period20/10/1120/10/14

Keywords

  • few-shot learning
  • knowledge transfer
  • object detection

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Few-Shot Object Detection via Knowledge Transfer'. Together they form a unique fingerprint.

Cite this