In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on NetVLAD and a triplet mining procedure based on samples difficulty to obtain an effective image representation. Extensive experiments show that our approach is able to reach state-of-the-art results on three standard datasets.
Image retrieval using multi-scale CNN features pooling / Vaccaro F.; Bertini M.; Uricchio T.; Del Bimbo A.. - ELETTRONICO. - (2020), pp. 311-315. (Intervento presentato al convegno 10th ACM International Conference on Multimedia Retrieval, ICMR 2020 tenutosi a irl nel 2020) [10.1145/3372278.3390732].
Image retrieval using multi-scale CNN features pooling
Vaccaro F.;Bertini M.;Uricchio T.;Del Bimbo A.
2020
Abstract
In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on NetVLAD and a triplet mining procedure based on samples difficulty to obtain an effective image representation. Extensive experiments show that our approach is able to reach state-of-the-art results on three standard datasets.
| File | Dimensione | Formato | |
|---|---|---|---|
|
2004.09695.pdf
accesso aperto
Descrizione: articolo principale
Tipologia:
Versione finale referata (Postprint, Accepted manuscript)
Licenza:
Tutti i diritti riservati
Dimensione
7.15 MB
Formato
Adobe PDF
|
7.15 MB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
