Image-text Pre-training For Logo Recognition

Abstract

Open-set logo recognition is commonly solved by first detecting possible logo regions and then matching the detected parts against an ever-evolving dataset of cropped logo images. The matching model, a metric learning problem, is especially challenging for logo recognition due to the mixture of text and symbols in logos. We propose two novel contributions to improve the matching model's performance: (a) using image-text paired samples for pre-training, and (b) an improved metric learning loss function. A standard paradigm of fine-tuning ImageNet pre-trained models fails to discover the text sensitivity necessary to solve the matching problem effectively. This work demonstrates the importance of pre-training on image-text pairs, which significantly improves the performance of a visual embedder trained for the logo retrieval task, especially for more text-dominant classes. We construct a composite public logo dataset combining LogoDet3K, OpenLogo, and FlickrLogos-47 deemed OpenLogoDet3K4

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keyhubenthal2023image

Related papers

• Open Set Logo Detection And Retrieval (2017)9.23
• Scalable Logo Recognition Using Proxies (2018)11.93
• A Deep One-shot Network For Query-based Logo Retrieval (2018)10.61
• Segment Augmentation And Differentiable Ranking For Logo Retrieval (2022)0.00
• Multi-label Logo Recognition And Retrieval Based On Weighted Fusion Of Neural Features (2022)6.34
• Imagebert: Cross-modal Pre-training With Large-scale Weak-supervised Image-text Data (2020)0.00
• Video Logo Retrieval Based On Local Features (2018)6.34
• Lexlip: Lexicon-bottlenecked Language-image Pre-training For Large-scale Image-text Retrieval (2023)10.85