SAD-ReID: Semantically-anchored dynamics for unsupervised vehicle re-identification

Engineering notes

Extensive experiments on the VeRi-776 and VehicleID benchmarks demonstrate the significant superiority of our approach over existing state-of-the-art methods, achieving an impressive Rank-1 accuracy of 90.0\% and 43.2\% mAP on VeRi-776.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

<title>Abstract</title> Unsupervised vehicle re-identification (Re-ID) is pivotal for scalable intelligent transportation systems but faces significant challenges from severe noise accumulation. Traditional clustering-based methods often suffer from error propagation during online training, as purely visual features are highly susceptible to intra-class viewpoint variations and inter-class similarities. To mitigate this fundamental limitation, we propose a novel Semantically-Anchored Dynamics (SAD-ReID) framework that exploits the viewpoint-invariant stability of text-induced semantic knowledge derived from Vision-Language Models. Specifically, we first introduce a Semantically-Guided Initialization strategy that fuses visual similarities with detailed textual descriptions generated automatically by Qwen-VL. This rectifies initial visual clusters to establish robust text-guided dual-prototype (visual and semantic) anchors. During the online learning phase, we propose a Reliability-Aware Dynamic Update (RADU) mechanism. By calculating a Cross-Modality Allegiance (CMA) score that measures the topological agreement between visual and textual spaces, RADU dynamically adjusts the memory update momentum. This efficiently accelerates learning from reliable samples while filtering out noisy pseudo-labels to prevent memory corruption. Furthermore, an Adaptive Granularity Attention Fusion (AGAF) module is designed to capture both global semantic attributes and fine-grained local discriminative details. Extensive experiments on the VeRi-776 and VehicleID benchmarks demonstrate the significant superiority of our approach over existing state-of-the-art methods, achieving an impressive Rank-1 accuracy of 90.0\% and 43.2\% mAP on VeRi-776. By enforcing text-visual semantic consistency throughout the evolutionary training process, SAD-ReID successfully prevents model drift and learns highly robust representations without any manual annotation.

Links and sources

Comments