A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification

TL;DR

This paper introduces a new theoretical framework for pseudo-labeling in unsupervised domain adaptive re-identification, providing general good practices and demonstrating consistent performance improvements across multiple datasets and methods.

Contribution

It presents a formal theoretical upper-bound for pseudo-labeling in UDA re-ID and derives practical good practices from this theory to enhance performance.

Findings

Consistent performance gains across multiple datasets.

Effective improvements for various state-of-the-art methods.

Theoretical insights guide practical enhancements.

Abstract

The use of pseudo-labels prevails in order to tackle Unsupervised Domain Adaptive (UDA) Re-Identification (re-ID) with the best performance. Indeed, this family of approaches has given rise to several UDA re-ID specific frameworks, which are effective. In these works, research directions to improve Pseudo-Labeling UDA re-ID performance are varied and mostly based on intuition and experiments: refining pseudo-labels, reducing the impact of errors in pseudo-labels... It can be hard to deduce from them general good practices, which can be implemented in any Pseudo-Labeling method, to consistently improve its performance. To address this key question, a new theoretical view on Pseudo-Labeling UDA re-ID is proposed. The contributions are threefold: (i) A novel theoretical framework for Pseudo-Labeling UDA re-ID, formalized through a new general learning upper-bound on the UDA re-ID performance. (ii) General good practices for Pseudo-Labeling, directly deduced from the interpretation of the proposed theoretical framework, in order to improve the target re-ID performance. (iii) Extensive experiments on challenging person and vehicle cross-dataset re-ID tasks, showing consistent performance improvements for various state-of-the-art methods and various proposed implementations of good practices.