Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918063911206912 |
|---|---|
| author | Kavimandan, Kshitij Nalmpantis, Angelos Beauxis-Aussalet, Emma Sips, Robert-Jan |
| author_facet | Kavimandan, Kshitij Nalmpantis, Angelos Beauxis-Aussalet, Emma Sips, Robert-Jan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13496 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval Kavimandan, Kshitij Nalmpantis, Angelos Beauxis-Aussalet, Emma Sips, Robert-Jan Computer Vision and Pattern Recognition Information Retrieval Machine Learning 68T45, 68T07 H.3.3; I.4.10; I.2.10 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. |
| title | Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval |
| topic | Computer Vision and Pattern Recognition Information Retrieval Machine Learning 68T45, 68T07 H.3.3; I.4.10; I.2.10 |
| url | https://arxiv.org/abs/2506.13496 |