Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval

TL;DR

This paper introduces a hierarchical multi-positive contrastive learning method that leverages patent taxonomy to improve image retrieval accuracy, especially for resource-constrained models, by utilizing hierarchical relationships in patent classifications.

Contribution

The paper proposes a novel hierarchical multi-positive contrastive loss that incorporates patent taxonomy into the retrieval process, enhancing performance with low-parameter models.

Findings

Improved retrieval accuracy on DeepPatent2 dataset.

Effective with low-parameter models, reducing computational requirements.

Leverages hierarchical patent classifications for better semantic understanding.

Abstract

Patent images are technical drawings that convey information about a patent's innovation. Patent image retrieval systems aim to search in vast collections and retrieve the most relevant images. Despite recent advances in information retrieval, patent images still pose significant challenges due to their technical intricacies and complex semantic information, requiring efficient fine-tuning for domain adaptation. Current methods neglect patents' hierarchical relationships, such as those defined by the Locarno International Classification (LIC) system, which groups broad categories (e.g., "furnishing") into subclasses (e.g., "seats" and "beds") and further into specific patent designs. In this work, we introduce a hierarchical multi-positive contrastive loss that leverages the LIC's taxonomy to induce such relations in the retrieval process. Our approach assigns multiple positive pairs to each patent image within a batch, with varying similarity scores based on the hierarchical taxonomy. Our experimental analysis with various vision and multimodal models on the DeepPatent2 dataset shows that the proposed method enhances the retrieval results. Notably, our method is effective with low-parameter models, which require fewer computational resources and can be deployed on environments with limited hardware.