一次知识迁移，适配多种设备的轻量行人重识别模型
One-Shot Knowledge Transfer for Scalable Person Re-Identification
- 用权重链一次性固化教师模型知识，避免重复训练
- 在多个模型尺寸下均优于现有压缩方法，最高提升4.2%
- 适合边缘计算场景，尤其适合资源受限的部署
行人重识别（ReID）中的边缘计算对减轻云端负载和保障用户隐私至关重要。传统压缩方法为每个学生模型单独进行计算，当需适配不同资源条件的多种模型时，导致重复且繁琐的训练过程。为此，我们提出一种新型知识继承方法OSKT（One-Shot Knowledge Transfer），将教师模型的知识凝聚到一个中间载体——权重链中。当下游场景需要满足特定资源约束的模型时，该权重链可无须额外计算直接扩展至目标规模。OSKT显著优于当前最优压缩方法，且具备一次知识迁移的优势，无需为每个目标模型重复计算。
原文摘要 · Abstract (English)
Edge computing in person re-identification (ReID) is crucial for reducing the load on central cloud servers and ensuring user privacy. Conventional compression methods for obtaining compact models require computations for each individual student model. When multiple models of varying sizes are needed to accommodate different resource conditions, this leads to repetitive and cumbersome computations. To address this challenge, we propose a novel knowledge inheritance approach named OSKT (One-Shot Knowledge Transfer), which consolidates the knowledge of the teacher model into an intermediate carrier called a weight chain. When a downstream scenario demands a model that meets specific resource constraints, this weight chain can be expanded to the target model size without additional computation. OSKT significantly outperforms state-of-the-art compression methods, with the added advantage of one-time knowledge transfer that eliminates the need for frequent computations for each target model.
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。