Robust Re-Identification by Multiple Views Knowledge Distillation
Abstract
To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion. However, these solutions face a large drop in performance for single image queries (e.g., Image-To-Video setting). Recent works address this severe degradation by transferring temporal information from a Video-based network to an Image-based one. In this work, we devise a training strategy that allows the transfer of a superior knowledge, arising from a set of views depicting the target object. Our proposal - Views Knowledge Distillation (VKD) - pins this visual variety as a supervision signal within a teacher-student framework, where the teacher educates a student who observes fewer views. As a result, the student outperforms not only its teacher but also the current state-of-the-art in Image-To-Video by a wide margin (6.3% mAP on MARS, 8.6% on Duke-Video-ReId and 5% on VeRi-776). A thorough analysis - on Person, Vehicle and Animal Re-ID - investigates the properties of VKD from a qualitatively and quantitatively perspective. Code is available at https://github.com/aimagelab/VKD.
Cite
Text
Porrello et al. "Robust Re-Identification by Multiple Views Knowledge Distillation." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58607-2_6Markdown
[Porrello et al. "Robust Re-Identification by Multiple Views Knowledge Distillation." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/porrello2020eccv-robust/) doi:10.1007/978-3-030-58607-2_6BibTeX
@inproceedings{porrello2020eccv-robust,
title = {{Robust Re-Identification by Multiple Views Knowledge Distillation}},
author = {Porrello, Angelo and Bergamini, Luca and Calderara, Simone},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58607-2_6},
url = {https://mlanthology.org/eccv/2020/porrello2020eccv-robust/}
}