.png){kind=icon}
.png){kind=icon}
Return
ProLFA: Representative prototype selection for local feature aggregation
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2019.11.073.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Given a set of hand-crafted local features, acquiring a global representation via aggregation is a promising technique to boost computational efficiency and improve task performance. Existing feature aggregation (FA) approaches, including Bag of Words and Fisher Vectors, usually fail to capture the desired information due to their pipeline mode. In this paper, we propose a generic formulation to provide a systematical solution (named ProLFA) to aggregate local descriptors. It is capable of producing compact yet interpretable representations by selecting representative prototypes from numerous descriptors, under relaxed exclusivity constraint. Meanwhile, to strengthen the discriminability of the aggregated representation, we rationally enforce the domain-invariant projection of bundled descriptors along a task-specific direction. Furthermore, ProLFA is also provided with a powerful generalization ability to deal flexibly with the semi-supervised and fully supervised scenarios in local feature aggregation. Experimental results on various descriptors and tasks demonstrate the proposed ProLFA is considerably superior over currently available alternatives about feature aggregation. (C) 2019 Published by Elsevier B.V.
Keywords:
Prototype selection
Feature aggregation
Block coordinate descent
Domain-invariant projection
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W