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

09/20/2020
by   Fabian Dubourvieux, et al.
0

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 adaptability to the target domain while ensuring 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.

READ FULL TEXT
research
01/06/2020

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

Person re-identification (re-ID) aims at identifying the same persons' i...
research
01/04/2021

Learn by Guessing: Multi-Step Pseudo-Label Refinement for Person Re-Identification

Unsupervised Domain Adaptation (UDA) methods for person Re-Identificatio...
research
10/27/2019

Hierarchical Clustering-guided re-ID with Triplet loss

For most unsupervised person re-identification (re-ID), people often ado...
research
10/15/2021

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

Unsupervised Domain Adaptation (UDA) for re-identification (re-ID) is a ...
research
12/24/2021

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

The use of pseudo-labels prevails in order to tackle Unsupervised Domain...
research
06/29/2021

Domain adaptation for person re-identification on new unlabeled data using AlignedReID++

In the world where big data reigns and there is plenty of hardware prepa...
research
06/11/2020

Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification

Unsupervised domain adaptation (UDA) for person re-identification is cha...

Please sign up or login with your details

Forgot password? Click here to reset