Unsupervised part learning for visual recognition - Archive ouverte HAL
Conference Papers Year : 2017

Unsupervised part learning for visual recognition

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 (1.38 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01507379 , version 1 (13-04-2017)

Identifiers

Cite

Ronan Sicre, Yannis Avrithis, Ewa Kijak, Frédéric Jurie. Unsupervised part learning for visual recognition. CVPR 2017 - IEEE Conference on Computer Vision and Pattern Recognition, Jul 2017, Honolulu, United States. ⟨hal-01507379⟩
411 View
381 Download

Altmetric

Share

More