SeeTek: Very Large-Scale Open-set Logo Recognition with Text-Aware Metric Learning

• Main Authors: Li, Chenge, Fehervari, Istvan, Zhao, Xiaonan, Macedo, Ives, Appalaraju, Srikar
• Format: Conference Proceeding
• Language: English
• Subjects: Computer vision; Feature extraction; Image/Video Indexing and Retrieval; Large-scale Vision Applications; Object Detection/Recognition/Categorization; Transfer; Few-shot; Semi- and Un- supervised Learning; Vision and Languages; Measurement; Predictive models; Text recognition; Training; Visualization
• ISSN: 2642-9381
• DOI: 10.1109/WACV51458.2022.00066

Recent advances in deep learning and computer vision have set new state of the art in logo recognition [2], [9], [36]. Logo recognition has mostly been approached as a closed-set object recognition problem and more recently as an open-set retrieval problem. Current approaches suffer from distinguishing visually similar logos, especially in open-set retrieval for very large-scale applications with thousands of brands. To address the problem, we propose a multi-task learning architecture of deep metric learning and scene text recognition. We use brand names as weak labels and enforce the model to simultaneously extract distinct visual features as well as predict brand name text. To achieve it, we collected a dataset with 3 Million logos cropped from Amazon Product Catalog images across nearly 8K brands, named PL8K. Our experiments show that adding the task of text recognition during training boosts the model's retrieval performance both on our PL8K dataset and on five other public logo datasets.