Unsupervised part learning for visual recognition

Ronan Sicre 1 Yannis Avrithis 2 Ewa Kijak 2 Frédéric Jurie 3
2 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
3 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal.inria.fr/hal-02370253
Contributor : Yannis Avrithis <>
Submitted on : Tuesday, November 19, 2019 - 1:13:39 PM
Last modification on : Thursday, November 21, 2019 - 1:21:05 AM

File

1704.03755.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02370253, version 1
  • ARXIV : 1704.03755

Citation

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

Share

Metrics

Record views

9

Files downloads

33