Unsupervised part learning for visual recognition - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Unsupervised part learning for visual recognition

(1) , (2) , (2) , (3)
1
2
3

Abstract

Part-based image classification aims at representing categories by small sets of learned discriminative parts, upon which an image representation is built. Considered as a promising avenue a decade ago, this direction has been neglected since the advent of deep neural networks. In this context, this paper brings two contributions: first, this work proceeds one step further compared to recent part-based models (PBM), focusing on how to learn parts without using any labeled data. Instead of learning a set of parts per class, as generally performed in the PBM literature, the proposed approach both constructs a partition of a given set of images into visually similar groups, and subsequently learns a set of discriminative parts per group in a fully unsu-pervised fashion. This strategy opens the door to the use of PBM in new applications where labeled data are typically not available, such as instance-based image retrieval. Second , this paper shows that despite the recent success of end-to-end models, explicit part learning can still boost classification performance. We experimentally show that our learned parts can help building efficient image representations , which outperform state-of-the art Deep Convolu-tional Neural Networks (DCNN) on both classification and retrieval tasks.
Fichier principal
Vignette du fichier
1704.03755.pdf (1.37 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02370253 , version 1 (19-11-2019)

Identifiers

Cite

Ronan Sicre, Yannis Avrithis, Ewa Kijak, Frédéric Jurie. Unsupervised part learning for visual recognition. 2017. ⟨hal-02370253⟩
28 View
46 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More