发表机构
School of Communications and Information Engineering, Xi’an University of Posts and Telecommunications; School of Artificial Intelligence, Hainan Normal University; School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University（西安邮电大学通信与信息工程学院; 海南师范大学人工智能学院; 西北工业大学人工智能与光电学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有细粒度轮胎识别技术的局限，提出含双分支独立推理和增强特征融合的轻量级方法，利用互模态信任、频域分层引导模块及轻量级重建正则化提升性能，建立数据集并经实验验证了算法优越性。
AI 中文摘要
视觉轮胎识别是车辆安全监测、自动驾驶感知和汽车自动维护的核心支撑技术。现有细粒度轮胎识别技术存在三个突出局限性。本文提出一种轻量级细粒度轮胎花纹识别方法，采用双分支独立推理和增强特征融合提升识别性能。该框架用两个专门分支分别提取轮胎表面和胎面压痕的特定模态判别特征，通过互模态信任实现跨模态互补特征增强。还设计了频域分层引导模块，引入轻量级重建正则化提高特征稳定性和识别鲁棒性。此外建立了MTire299多源数据集。实验验证了算法的优越性和有效性。
英文摘要
Visual tire recognition serves as a core supporting technique for vehicle safety monitoring, autonomous driving perception and automated automotive maintenance. Existing fine-grained tire recognition techniques suffer from three prominent limitations. They tend to depend on only one visual source, lack the capacity to jointly model spatial and frequency cues for minute tread texture extraction, and suffer severe overfitting given limited annotated tire imagery. This paper proposes a lightweight fine-grained tire pattern recognition method incorporating dual-branch independent inference and enhanced feature fusion to boost recognition performance. The framework employs two task-specialized branches dedicated to tire surface and tread indentation, respectively, to extract modality-specific discriminative features. Each branch conducts independent prediction, while cross-branch feature fusion exploits Mutual Modality Trust (M$^2$T) to realize complementary feature enhancement across two modalities. Besides, a frequency-domain hierarchical guidance module is devised, which leverages bandpass filters to decompose feature maps into high- and low-frequency components and enables fine-grained cross-layer feature modulation. Furthermore, a Lightweight Reconstruction Regularization (LR$^2$) is introduced to retain abundant intrinsic information within feature embeddings, substantially improving feature stability and recognition robustness under limited labeled training data. In addition, we establish a surface-indentation multi-source dataset namely MTire299 for fine-grained tire tread recognition, which covers 299 categories with a total of 14795 paired image samples. Extensive experiments conducted on two public tire datasets validate the superiority and efficacy of the proposed algorithm.
