One-Shot Knowledge Transfer for Scalable Person Re-Identification

TL;DR

This paper introduces OSKT, a one-shot knowledge transfer method for scalable person re-identification that efficiently creates multiple resource-adapted models from a single teacher, reducing computational overhead.

Contribution

The paper proposes a novel knowledge inheritance approach called OSKT that consolidates knowledge into a weight chain, enabling scalable model adaptation without repeated training.

Findings

OSKT outperforms existing compression methods in re-identification tasks.

It allows quick adaptation to different resource constraints without additional training.

The approach reduces computational costs in deploying multiple models.

Abstract

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.