Abstract
• Person re-identification problem statement. • Novel unsupervised single-source multiple-target domain adaptation setup. • Loss function modeled around triplet loss. • Tackling catastrophic forgetting in source domain using domain adaptive methods. • Ensuring competitive performance across source and all target domains. The task of unsupervised domain adaptive (DA) person re-identification (reID) has gained prominence in recent years. Current reID works mostly leverage off-the-shelf single-target domain adaptive (STDA) techniques to reduce any domain gap between a labeled source dataset and an unlabeled target dataset in a single-source single-target training setup in their reID framework. However, directly extending such STDA techniques to multiple target domains suffers from two inherent drawbacks: a) the performance on the source domain deteriorates once the model is fine-tuned for a target domain, and b) posing the single-source multi-target (SSMT) setup as an independent single-source single-target case by blending all target domains to form a single target domain fails to utilize the complementary information present in the different target domains. Hence, to tackle this problem of unsupervised multi-target domain adaptation (MTDA), we propose a novel architecture called SSMTReID-Net. SSMTReID-Net employs the elastic weight consolidation (EWC) regularizer to ensure competitive performance on the source domain after adaptation, and the notion of information bottleneck (IB) to highlight domain invariant target features while suppressing any domain-irrelevant artifacts . Our model is end-to-end trainable, and extensive results on different single-source multi-target combinations of challenging person reID datasets like DukeMTMC-reID, Market-1501 and CUHK03 datasets confirm the superiority of SSMTReID-Net over the other baselines.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.