Unsupervised Trademark Retrieval Method Based on Attention Mechanism

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 5; p. 1894
• Main Authors: Cao, Jiangzhong, Huang, Yunfei, Dai, Qingyun, Ling, Wing-Kuen
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 08-03-2021; MDPI
• Subjects: attention mechanism; Deep learning; Experiments; Image retrieval; instance discrimination; Intellectual property; local cross-channel interaction; Neural networks; Research methodology; Semantics; Supervised learning; Teaching methods; trademark retrieval; Trademarks; attention mechanism; local cross-channel interaction; instance discrimination; trademark retrieval
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s21051894

Aiming at the high cost of data labeling and ignoring the internal relevance of features in existing trademark retrieval methods, this paper proposes an unsupervised trademark retrieval method based on attention mechanism. In the proposed method, the instance discrimination framework is adopted and a lightweight attention mechanism is introduced to allocate a more reasonable learning weight to key features. With an unsupervised way, this proposed method can obtain good feature representation of trademarks and improve the performance of trademark retrieval. Extensive comparative experiments on the METU trademark dataset are conducted. The experimental results show that the proposed method is significantly better than traditional trademark retrieval methods and most existing supervised learning methods. The proposed method obtained a smaller value of NAR (Normalized Average Rank) at 0.051, which verifies the effectiveness of the proposed method in trademark retrieval.