Unsupervised Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval

TL;DR

This paper introduces an unsupervised, part-based weighting method for deep convolutional features that improves image retrieval by highlighting discriminative object parts and suppressing background noise, outperforming existing methods.

Contribution

It presents a novel unsupervised strategy to select semantic part detectors for weighted feature aggregation in image retrieval.

Findings

Outperforms state-of-the-art unsupervised methods

Effective in highlighting discriminative object parts

Demonstrates robustness across four standard datasets

Abstract

In this paper, we propose a simple but effective semantic part-based weighting aggregation (PWA) for image retrieval. The proposed PWA utilizes the discriminative filters of deep convolutional layers as part detectors. Moreover, we propose the effective unsupervised strategy to select some part detectors to generate the "probabilistic proposals", which highlight certain discriminative parts of objects and suppress the noise of background. The final global PWA representation could then be acquired by aggregating the regional representations weighted by the selected "probabilistic proposals" corresponding to various semantic content. We conduct comprehensive experiments on four standard datasets and show that our unsupervised PWA outperforms the state-of-the-art unsupervised and supervised aggregation methods. Code is available at https://github.com/XJhaoren/PWA.