Learning discriminative, view-invariant and multi-scale representations of person appearance with different semantic levels is of paramount importance for person Re-Identification (Re-ID). A surge of effort has been spent by the community to learn deep Re-ID models capturing a holistic single semantic level feature representation. To improve the achieved results, additional visual attributes and body part-driven models have been considered. However, these require extensive human annotation labor or demand additional computational efforts. We argue that a pyramid-inspired method capturing multi-scale information may overcome such requirements. Precisely, multi-scale stripes that represent visual information of a person can be used by a novel architecture factorizing them into latent discriminative factors at multiple semantic levels. A multi-task loss is combined with a curriculum learning strategy to learn a discriminative and invariant person representation which is exploited for triplet-similarity learning. Results on three benchmark Re-ID datasets demonstrate that better performance than existing methods are achieved (e.g., more than 90% accuracy on the Duke-MTMC dataset).

Aggregating Deep Pyramidal Representations for Person Re-Identification

Martinel N.
Primo
;
Foresti G. L.;Micheloni C.
2019-01-01

Abstract

Learning discriminative, view-invariant and multi-scale representations of person appearance with different semantic levels is of paramount importance for person Re-Identification (Re-ID). A surge of effort has been spent by the community to learn deep Re-ID models capturing a holistic single semantic level feature representation. To improve the achieved results, additional visual attributes and body part-driven models have been considered. However, these require extensive human annotation labor or demand additional computational efforts. We argue that a pyramid-inspired method capturing multi-scale information may overcome such requirements. Precisely, multi-scale stripes that represent visual information of a person can be used by a novel architecture factorizing them into latent discriminative factors at multiple semantic levels. A multi-task loss is combined with a curriculum learning strategy to learn a discriminative and invariant person representation which is exploited for triplet-similarity learning. Results on three benchmark Re-ID datasets demonstrate that better performance than existing methods are achieved (e.g., more than 90% accuracy on the Duke-MTMC dataset).
2019
978-1-7281-2506-0
File in questo prodotto:
File Dimensione Formato  
Martinel_Aggregating_Deep_Pyramidal_Representations_for_Person_Re-Identification_CVPRW_2019_paper.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 15.06 MB
Formato Adobe PDF
15.06 MB Adobe PDF Visualizza/Apri
foresti2.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Non pubblico
Dimensione 1.16 MB
Formato Adobe PDF
1.16 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11390/1187047
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 49
  • ???jsp.display-item.citation.isi??? ND
social impact