Logo-VGR: Visual Grounded Reasoning for Open-world Logo Recognition
Authors:
- Zichen LiangZLZichen Liang
- Fei YangFYFei Yang
- Xialei LiuXLXialei Liu
Preprint
Abstract
Recent advances in multimodal large language models (MLLMs) have been primarily evaluated on general-purpose benchmarks, while their applications in domain-specific scenarios, such as intelligent product moderation, remain underexplored. To address this gap, we introduce an open-world logo recognition benchmark, a core challenge in product moderation. Unlike traditional logo recognition methods that rely on memorizing representations of tens of thousands of brands-an impractical approach in real-world settings-our proposed method, Logo-VGR, enables generalization to large-scale brand recognition with supervision from only a small subset of brands. Specifically, we reformulate logo recognition as a comparison-based task, requiring the model to match product images with candidate logos rather than directly generating brand labels. We further observe that existing models tend to overfit by memorizing brand distributions instead of learning robust multimodal reasoning, which results in poor performance on unseen brands. To overcome this limitation, Logo-VGR introduces a new paradigm of domain-specific multimodal reasoning: Logo Perception Grounding injects domain knowledge, and Logo-Guided Visual Grounded Reasoning enhances the model's reasoning capability. Experimental results show that Logo-VGR outperforms strong baselines by nearly 10 points in OOD settings, demonstrating superior generalization.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- DR-YOLO: dual reconstructed YOLO for logo detection in livestreamingMultimedia Systems, 2025
- Context-based modeling for accurate logo detection in complex environmentsJournal of Visual Communication and Image Representation, 2024
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model2023
- Visual Instruction Tuning2023
- LogoDet-3K: A Large-scale Image Dataset for Logo DetectionACM Transactions on Multimedia Computing, Communications, and Applications, 2022