VisNet通过多尺度融合与动态学习，实现高效高精度行人重识别。
VisNet: Efficient Person Re-Identification via Alpha-Divergence Loss, Feature Fusion and Dynamic Multi-Task Learning
- 多尺度特征融合+自动注意力，提升表征能力
- 在Market-1501上达87.05% Rank-1，仅需4.601 GFLOPs
- 适合资源受限的实时监控与移动端部署
行人重识别（ReID）在监控和移动应用中至关重要，需兼顾高精度与低计算开销。现有先进方法虽精度高，但计算成本过大。为此，本文提出VisNet，一种高效且有效的重识别模型，适用于真实场景。其核心包括：多尺度特征融合（整合ResNet50阶段1至4，无并行路径）、基于规则伪标签的语义聚类引入空间约束、动态权重平均平衡分类正则化，以及使用FIDI损失函数优化度量学习。VisNet在Market-1501数据集上达到87.05% Rank-1和77.65% mAP，参数量32.41M，计算量4.601 GFLOPs，为计算资源有限的监控与移动端提供了实用的实时部署方案。
原文摘要 · Abstract (English)
Person re-identification (ReID) is an extremely important area in both surveillance and mobile applications, requiring strong accuracy with minimal computational cost. State-of-the-art methods give good accuracy but with high computational budgets. To remedy this, this paper proposes VisNet, a computationally efficient and effective re-identification model suitable for real-world scenarios. It is the culmination of conceptual contributions, including feature fusion at multiple scales with automatic attention on each, semantic clustering with anatomical body partitioning, a dynamic weight averaging technique to balance classification semantic regularization, and the use of loss function FIDI for improved metric learning tasks. The multiple scales fuse ResNet50's stages 1 through 4 without the use of parallel paths, with semantic clustering introducing spatial constraints through the use of rule-based pseudo-labeling. VisNet achieves 87.05% Rank-1 and 77.65% mAP on the Market-1501 dataset, having 32.41M parameters and 4.601 GFLOPs, hence, proposing a practical approach for real-time deployment in surveillance and mobile applications where computational resources are limited.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。