Learning Efficient Representations for Image-Based Patent Retrieval

TL;DR

This paper introduces a simple, lightweight model for content-based image patent retrieval that significantly outperforms existing methods and achieves state-of-the-art results on large-scale benchmarks.

Contribution

The paper presents a novel, efficient model tailored for image-based patent retrieval, outperforming previous approaches and setting new benchmarks.

Findings

Outperforms counterparts with a 33.5% improvement in mAP

Achieves a high mAP of 93.5% when scaled up

Ranks first in the ECCV 2022 Patent Diagram Image Retrieval Challenge

Abstract

Patent retrieval has been attracting tremendous interest from researchers in intellectual property and information retrieval communities in the past decades. However, most existing approaches rely on textual and metadata information of the patent, and content-based image-based patent retrieval is rarely investigated. Based on traits of patent drawing images, we present a simple and lightweight model for this task. Without bells and whistles, this approach significantly outperforms other counterparts on a large-scale benchmark and noticeably improves the state-of-the-art by 33.5% with the mean average precision (mAP) score. Further experiments reveal that this model can be elaborately scaled up to achieve a surprisingly high mAP of 93.5%. Our method ranks first in the ECCV 2022 Patent Diagram Image Retrieval Challenge.