Infinite-dimensional feature aggregation via a factorized bilinear model

doi:10.1016/j.patcog.2021.108397

Infinite-dimensional feature aggregation via a factorized bilinear model

2022-04-01

1

PRE

AI

DOI：10.1016/j.patcog.2021.108397

Original

Original request for help

Save

Abstract

En 中文

Aggregating infinite-dimensional features has demonstrated superiority compared with their finite dimensional counterparts. However, most existing methods approximate infinite-dimensional features with finite-dimensional representations, which inevitably results in approximation error and inferior performance. In this paper, we propose a non-approximate aggregation method that directly aggregates infinite-dimensional features rather than relying on approximation strategies. Specifically, since infinite dimensional features are infeasible to store, represent and compute explicitly, we introduce a factorized bilinear model to capture pairwise second-order statistics of infinite-dimensional features as a global descriptor. It enables the resulting aggregation formulation to only involve the inner product in an infinite-dimensional space. The factorized bilinear model is calculated by a Sigmoid kernel to generate informative features containing infinite order statistics. Experiments on four visual tasks including the fine-grained, indoor scene, texture, and material classification, demonstrate that our method consistently achieves the state-of-the-art performance. (c) 2021 Elsevier Ltd. All rights reserved.

Keywords:

Feature aggregation

Infinite-dimensional features

Non-approximate method

Second-order statistics

Infinite-dimensional feature aggregation via a factorized bilinear model

Abstract

Journal

Organization