Learning Efficient Representations for Image-Based Patent Retrieval
This addresses a gap in patent retrieval for intellectual property and information retrieval communities by focusing on image-based methods, though it appears incremental as it builds on existing retrieval tasks.
The paper tackles the problem of content-based image retrieval for patent drawings, presenting a lightweight model that improves state-of-the-art by 33.5% in mean average precision and achieves up to 93.5% mAP in scaled experiments.
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.