面向行人重识别的 SSM 感知词元高效 VMamba：自适应图像块剪枝与合并
SSM-Aware Token-Efficient VMamba via Adaptive Patch Pruning and Merging for Person Re-Identification
把视觉状态空间模型（VMamba）中冗余的词元按层自适应剪枝、按深度合并，并学习逐层阈值来动态权衡精度与算力；做视觉主干加速的人可直接把这套结构化词元削减策略迁移到 ViT/SSM 类骨干上。
原文依据 TE-VMamba reduces FLOPs by over 60%, achieving significant computational savings while maintaining competitive accuracy.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论行人重识别（Re-ID）在实际部署中需要在判别能力与计算效率之间取得平衡。然而，即便是具有线性复杂度的视觉状态空间模型（SSM），也会因稠密的词元处理而存在冗余计算。我们提出 SSM 感知的词元高效 VMamba（TE-VMamba），它集成了自适应图像块剪枝与合并模块，在减少冗余词元的同时保留身份判别线索。层自适应剪枝策略在浅层移除低重要性词元以提升效率，而深度感知合并策略在深层聚合语义相似的词元以提升表示紧凑性。可学习的逐层阈值在整个网络中动态平衡精度与计算开销。在 Market-1501 基准上，TE-VMamba 将浮点运算量降低 60% 以上，在保持有竞争力精度的同时实现了显著的计算节省。这些结果凸显了状态空间模型中结构化词元削减在高效且强大的行人重识别方面的潜力。
英文原文摘要 1122 字符
Person re-identification (Re-ID) requires a balance between discriminative capability and computational efficiency for real-world deployment. However, even the Visual State Space Model (SSM), despite its linear complexity, suffers from redundant computation due to dense token processing. We propose SSM-aware Token-Efficient VMamba (TE-VMamba), which integrates adaptive patch pruning and merging modules to reduce redundant tokens while preserving identity-discriminative cues. The layer-adaptive pruning strategy removes low-importance tokens in shallow layers to enhance efficiency, whereas the depth-aware merging strategy consolidates semantically similar tokens in deeper layers to improve representation compactness. Learnable layer-wise thresholds dynamically balance accuracy and computational cost across the network. On the Market-1501 benchmark, TE-VMamba reduces FLOPs by over 60%, achieving significant computational savings while maintaining competitive accuracy. These results highlight the potential of structured token reduction in state-space models for efficient and powerful person re-identification.