Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
arXiv:2003.07618 · doi:10.1109/ICPR48806.2021.9412598
Abstract
This work considers the problem of domain shift in person re-identification.Being trained on one dataset, a re-identification model usually performs much worse on unseen data. Partially this gap is caused by the relatively small scale of person re-identification datasets (compared to face recognition ones, for instance), but it is also related to training objectives. We propose to use the metric learning objective, namely AM-Softmax loss, and some additional training practices to build well-generalizing, yet, computationally efficient models. We use recently proposed Omni-Scale Network (OSNet) architecture combined with several training tricks and architecture adjustments to obtain state-of-the art results in cross-domain generalization problem on a large-scale MSMT17 dataset in three setups: MSMT17-all->DukeMTMC, MSMT17-train->Market1501 and MSMT17-all->Market1501.
Submitted to International Conference on Pattern Recognition (ICPR 2020)
References in corpus (9)
- Res2Net: A New Multi-scale Backbone Architecture
- On the Convergence of Adam and Beyond
- Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
- Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project
- ABD-Net: Attentive but Diverse Person Re-Identification
- Learning Generalisable Omni-Scale Representations for Person Re-Identification
- Attention: A Big Surprise for Cross-Domain Person Re-Identification
- Fairest of Them All: Establishing a Strong Baseline for Cross-Domain Person ReID
- Fast and Accurate Person Re-Identification with RMNet