2021
DOI: 10.48550/arxiv.2108.02959
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Abstract: Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time. Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database. In this way, when updating the deployed model, we can bypass the inflexible and time-consuming feature re-extraction process. However, the old feature space that needs to be compatible is not ideal and faces the distribution discrepanc… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Publication Types

Select...

Relationship

0
0

Authors

Journals

citations
Cited by 0 publications
references
References 40 publications
(59 reference statements)
0
0
0
Order By: Relevance

No citations

Set email alert for when this publication receives citations?