A Large-scale Dataset and Benchmark for Similar Trademark Retrieval

TL;DR

This paper introduces a large-scale dataset and benchmark for trademark retrieval, evaluates existing methods, addresses key issues affecting performance, and applies deep learning models for the first time in this context.

Contribution

Provides a comprehensive large-scale dataset and benchmark for systematic evaluation of trademark retrieval methods, including addressing previously overlooked issues and applying deep learning techniques.

Findings

Benchmark enables systematic evaluation of TR approaches

Addressing contrast reversal and irrelevant text improves TR accuracy

Deep learning models show promising results in TR tasks

Abstract

Trademark retrieval (TR) has become an important yet challenging problem due to an ever increasing trend in trademark applications and infringement incidents. There have been many promising attempts for the TR problem, which, however, fell impracticable since they were evaluated with limited and mostly trivial datasets. In this paper, we provide a large-scale dataset with benchmark queries with which different TR approaches can be evaluated systematically. Moreover, we provide a baseline on this benchmark using the widely-used methods applied to TR in the literature. Furthermore, we identify and correct two important issues in TR approaches that were not addressed before: reversal of contrast, and presence of irrelevant text in trademarks severely affect the TR methods. Lastly, we applied deep learning, namely, several popular Convolutional Neural Network models, to the TR problem. To the best of the authors, this is the first attempt to do so.