Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling

TL;DR

This paper proposes a novel unsupervised domain adaptation framework for person re-identification that leverages both source and pseudo-labeled target data throughout training, improving robustness and performance.

Contribution

It introduces a two-branch architecture that combines classification and metric learning, utilizing source labels and pseudo-labels simultaneously for better domain adaptation.

Findings

Achieves state-of-the-art results on Market-1501 and DukeMTMC-reID datasets.

Outperforms existing methods on the challenging MSMT dataset.

Enhances robustness to pseudo-label noise in unsupervised domain adaptation.

Abstract

Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a different domain from the training data domain (source data). Unsupervised Domain Adaptation (UDA) is an interesting research direction for this challenge as it avoids a costly annotation of the target data. Pseudo-labeling methods achieve the best results in UDA-based re-ID. Surprisingly, labeled source data are discarded after this initialization step. However, we believe that pseudo-labeling could further leverage the labeled source data in order to improve the post-initialization training steps. In order to improve robustness against erroneous pseudo-labels, we advocate the exploitation of both labeled source data and pseudo-labeled target data during all training iterations. To support our guideline, we introduce a framework which relies on a two-branch architecture optimizing classification and triplet loss based metric learning in source and target domains, respectively, in order to allow \emph{adaptability to the target domain} while ensuring \emph{robustness to noisy pseudo-labels}. Indeed, shared low and mid-level parameters benefit from the source classification and triplet loss signal while high-level parameters of the target branch learn domain-specific features. Our method is simple enough to be easily combined with existing pseudo-labeling UDA approaches. We show experimentally that it is efficient and improves performance when the base method has no mechanism to deal with pseudo-label noise or for hard adaptation tasks. Our approach reaches state-of-the-art performance when evaluated on commonly used datasets, Market-1501 and DukeMTMC-reID, and outperforms the state of the art when targeting the bigger and more challenging dataset MSMT.