Trademark Similarity Evaluation Using a Combination of ViT and Local Features
The origin of the trademark similarity analysis problem lies within the legal area, specifically the protection of intellectual property. One of the possible technical solutions for this issue is the trademark similarity evaluation pipeline based on the content-based image retrieval approach. CNN-ba...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/7/398 |
| _version_ | 1797588887239917568 |
|---|---|
| author | Dmitry Vesnin Dmitry Levshun Andrey Chechulin |
| author_facet | Dmitry Vesnin Dmitry Levshun Andrey Chechulin |
| author_sort | Dmitry Vesnin |
| collection | DOAJ |
| description | The origin of the trademark similarity analysis problem lies within the legal area, specifically the protection of intellectual property. One of the possible technical solutions for this issue is the trademark similarity evaluation pipeline based on the content-based image retrieval approach. CNN-based off-the-shelf features have shown themselves as a good baseline for trademark retrieval. However, in recent years, the computer vision area has been transitioning from CNNs to a new architecture, namely, Vision Transformer. In this paper, we investigate the performance of off-the-shelf features extracted with vision transformers and explore the effects of pre-, post-processing, and pre-training on big datasets. We propose the enhancement of the trademark similarity evaluation pipeline by joint usage of global and local features, which leverages the best aspects of both approaches. Experimental results on the METU Trademark Dataset show that off-the-shelf features extracted with ViT-based models outperform off-the-shelf features from CNN-based models. The proposed method achieves a mAP value of 31.23, surpassing previous state-of-the-art results. We assume that the usage of an enhanced trademark similarity evaluation pipeline allows for the improvement of the protection of intellectual property with the help of artificial intelligence methods. Moreover, this approach enables one to identify cases of unfair use of such data and form an evidence base for litigation. |
| first_indexed | 2024-03-11T00:58:24Z |
| format | Article |
| id | doaj.art-1b5d82ae87d041d7be07b898b4ec52cd |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T00:58:24Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-1b5d82ae87d041d7be07b898b4ec52cd2023-11-18T19:47:05ZengMDPI AGInformation2078-24892023-07-0114739810.3390/info14070398Trademark Similarity Evaluation Using a Combination of ViT and Local FeaturesDmitry Vesnin0Dmitry Levshun1Andrey Chechulin2St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), 199178 St. Petersburg, RussiaSt. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), 199178 St. Petersburg, RussiaSt. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS), 199178 St. Petersburg, RussiaThe origin of the trademark similarity analysis problem lies within the legal area, specifically the protection of intellectual property. One of the possible technical solutions for this issue is the trademark similarity evaluation pipeline based on the content-based image retrieval approach. CNN-based off-the-shelf features have shown themselves as a good baseline for trademark retrieval. However, in recent years, the computer vision area has been transitioning from CNNs to a new architecture, namely, Vision Transformer. In this paper, we investigate the performance of off-the-shelf features extracted with vision transformers and explore the effects of pre-, post-processing, and pre-training on big datasets. We propose the enhancement of the trademark similarity evaluation pipeline by joint usage of global and local features, which leverages the best aspects of both approaches. Experimental results on the METU Trademark Dataset show that off-the-shelf features extracted with ViT-based models outperform off-the-shelf features from CNN-based models. The proposed method achieves a mAP value of 31.23, surpassing previous state-of-the-art results. We assume that the usage of an enhanced trademark similarity evaluation pipeline allows for the improvement of the protection of intellectual property with the help of artificial intelligence methods. Moreover, this approach enables one to identify cases of unfair use of such data and form an evidence base for litigation.https://www.mdpi.com/2078-2489/14/7/398trademarksdata protectionartificial intelligenceimage processingtrademark retrieval |
| spellingShingle | Dmitry Vesnin Dmitry Levshun Andrey Chechulin Trademark Similarity Evaluation Using a Combination of ViT and Local Features Information trademarks data protection artificial intelligence image processing trademark retrieval |
| title | Trademark Similarity Evaluation Using a Combination of ViT and Local Features |
| title_full | Trademark Similarity Evaluation Using a Combination of ViT and Local Features |
| title_fullStr | Trademark Similarity Evaluation Using a Combination of ViT and Local Features |
| title_full_unstemmed | Trademark Similarity Evaluation Using a Combination of ViT and Local Features |
| title_short | Trademark Similarity Evaluation Using a Combination of ViT and Local Features |
| title_sort | trademark similarity evaluation using a combination of vit and local features |
| topic | trademarks data protection artificial intelligence image processing trademark retrieval |
| url | https://www.mdpi.com/2078-2489/14/7/398 |
| work_keys_str_mv | AT dmitryvesnin trademarksimilarityevaluationusingacombinationofvitandlocalfeatures AT dmitrylevshun trademarksimilarityevaluationusingacombinationofvitandlocalfeatures AT andreychechulin trademarksimilarityevaluationusingacombinationofvitandlocalfeatures |