ProLFA: Representative Prototype Selection for Local Feature Aggregation

TL;DR

ProLFA introduces a systematic prototype selection method for local feature aggregation that produces compact, interpretable, and discriminative global representations, improving efficiency and performance across various tasks.

Contribution

It presents a novel, flexible formulation for feature aggregation that selects representative prototypes and enforces domain-invariant projections, applicable in semi-supervised and supervised settings.

Findings

ProLFA outperforms existing aggregation methods on multiple descriptors and tasks.

It produces more compact and discriminative representations.

Experimental results validate its superior performance and generalization ability.

Abstract

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 that the proposed ProLFA is considerably superior over currently available alternatives about feature aggregation.