Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters

TL;DR

This paper introduces HyPASS, a method for automatic hyperparameter tuning in unsupervised domain adaptation for re-identification, improving pseudo-labeling clustering performance without requiring target domain labels.

Contribution

It proposes a theoretically grounded, automatic, cyclic hyperparameter tuning method for pseudo-labeling in UDA re-ID, incorporating source validation and domain alignment modules.

Findings

HyPASS consistently improves state-of-the-art re-ID performance.

HyPASS reduces the need for empirical hyperparameter setting.

Experiments validate HyPASS's effectiveness across multiple datasets.

Abstract

Unsupervised Domain Adaptation (UDA) for re-identification (re-ID) is a challenging task: to avoid a costly annotation of additional data, it aims at transferring knowledge from a domain with annotated data to a domain of interest with only unlabeled data. Pseudo-labeling approaches have proven to be effective for UDA re-ID. However, the effectiveness of these approaches heavily depends on the choice of some hyperparameters (HP) that affect the generation of pseudo-labels by clustering. The lack of annotation in the domain of interest makes this choice non-trivial. Current approaches simply reuse the same empirical value for all adaptation tasks and regardless of the target data representation that changes through pseudo-labeling training phases. As this simplistic choice may limit their performance, we aim at addressing this issue. We propose new theoretical grounds on HP selection for clustering UDA re-ID as well as method of automatic and cyclic HP tuning for pseudo-labeling UDA clustering: HyPASS. HyPASS consists in incorporating two modules in pseudo-labeling methods: (i) HP selection based on a labeled source validation set and (ii) conditional domain alignment of feature discriminativeness to improve HP selection based on source samples. Experiments on commonly used person re-ID and vehicle re-ID datasets show that our proposed HyPASS consistently improves the best state-of-the-art methods in re-ID compared to the commonly used empirical HP setting.