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.
Robust Re-Identification by Multiple Views Knowledge Distillation / Porrello, Angelo; Bergamini, Luca; Calderara, Simone. - (2020). ((Intervento presentato al convegno European Conference on Computer Vision (ECCV) 2020 tenutosi a Glasgow, Scotland, UK nel August 23–28, 2020.
Data di pubblicazione: | 2020 | |
Titolo: | Robust Re-Identification by Multiple Views Knowledge Distillation | |
Autore/i: | Porrello, Angelo; Bergamini, Luca; Calderara, Simone | |
Autore/i UNIMORE: | ||
Codice identificativo Scopus: | 2-s2.0-85097428860 | |
Nome del convegno: | European Conference on Computer Vision (ECCV) 2020 | |
Luogo del convegno: | Glasgow, Scotland, UK | |
Data del convegno: | August 23–28, 2020 | |
Citazione: | Robust Re-Identification by Multiple Views Knowledge Distillation / Porrello, Angelo; Bergamini, Luca; Calderara, Simone. - (2020). ((Intervento presentato al convegno European Conference on Computer Vision (ECCV) 2020 tenutosi a Glasgow, Scotland, UK nel August 23–28, 2020. | |
Tipologia | Relazione in Atti di Convegno |
File in questo prodotto:
File | Descrizione | Tipologia | |
---|---|---|---|
main.pdf | Articolo principale | Post-print dell'autore (bozza post referaggio) | Open Access Visualizza/Apri |
Pubblicazioni consigliate

I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris