Knowledge Transfer in Vision Recognition: A Survey

Ying Lu (1) , Lingkun Luo (1) , Di Huang (1) , Alexandre Saidi (1) , Yunhong Wang (2) , Liming Chen (1)

1 imagine - Extraction de Caractéristiques et Identification
2 BUAA - Beihang University

In this survey, we propose to explore and discuss the common rules behind knowledge transfer works for vision recognition tasks. To achieve this, we firstly discuss the different kinds of reusable knowledge existing in a vision recognition task, then we categorize different knowledge transfer approaches depending on where the knowledge come from and where the knowledge go to. This viewpoint is different to previous surveys on knowledge transfer. We further show that some potential research directions could be induced based on our categorization methodology.

Mots clés: transfer learning; vision recognition; computer vision; machine learning

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Ying Lu, Lingkun Luo, Di Huang, Alexandre Saidi, Yunhong Wang, et al.. Knowledge Transfer in Vision Recognition: A Survey. 2019. ⟨hal-02101005v1⟩