Learning Efficient Representations for Image-Based Patent Retrieval

Hongsong Wang, Yuqi Zhang
8/26/2023
cs.CV

No official code found. Best implementation: hongsong-wang/Image-Based_Patent_Retrieval (1 star, last commit 2025-08-07).

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.

View on arXivView PDF

Code Implementations(1)

hongsong-wang/Image-Based_Patent_RetrievalCommunity71%

Learning Efficient Representations for Image-Based Patent Retrieval

10Aug 7, 20251 years ago

Similar Papers

Large Language Model Informed Patent Image Retrieval

86% match2024

Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval

82% match2025

PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures

81% match1 repo272025

FullRecall: A Semantic Search-Based Ranking Approach for Maximizing Recall in Patent Retrieval

80% match2025

PatentMatch: A Dataset for Matching Patent Claims & Prior Art

79% match1 repo492020

PatentVision: A multimodal method for drafting patent applications

77% match2025

Cite this paper

@article{wang2023learning,
  title  = {Learning Efficient Representations for Image-Based Patent Retrieval},
  author = {Hongsong Wang and Yuqi Zhang},
  year   = {2023},
  eprint = {2308.13749},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.13749v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.13749.svg)](https://codeofpaper.com/paper/2308.13749)

Discussion