Mutual Modality Trust with Lightweight Reconstruction Regularization for Fine-grained Tire Pattern Recognition
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address challenges in recognizing detailed tire tread patterns from images, which is important for vehicle safety and maintenance. They propose a new method that uses two separate processing branches to analyze different tire features and combines their information for better recognition. Their approach also breaks down image features into different frequency parts to better capture fine details and uses a special technique to keep important information during training, helping with limited data. They created a new dataset with many tire images to test their method and showed it works well compared to others.
fine-grained recognitiontire treadfeature fusionfrequency domainbandpass filtersregularizationimage classificationmulti-source datasetmutual modality trust
Authors
Jianning Yang, Jie Fang, Xinda Ma, Zirui Song, Dianwei Wang, Nan Wang
Abstract
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.