Localizing Objects with Self-Supervised Transformers and no Labels - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Localizing Objects with Self-Supervised Transformers and no Labels

Oriane Siméoni
  • Function : Author
  • PersonId : 1086486
Gilles Puy
Spyros Gidaris
  • Function : Author
Andrei Bursuc
Patrick Pérez
  • Function : Author
  • PersonId : 1064372

Abstract

Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer pre-trained in a self-supervised manner. Our method, LOST, does not require any external object proposal nor any exploration of the image collection; it operates on a single image. Yet, we outperform state-of-the-art object discovery methods by up to 8 CorLoc points on PASCAL VOC 2012. We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points. Moreover, we show promising results on the unsupervised object discovery task. The code to reproduce our results can be found at https://github.com/valeoai/LOST.

Dates and versions

hal-03541602 , version 1 (24-01-2022)

Identifiers

Cite

Oriane Siméoni, Gilles Puy, Huy V. Vo, Simon Roburin, Spyros Gidaris, et al.. Localizing Objects with Self-Supervised Transformers and no Labels. BMVC 2021 - 32nd British Machine Vision Conference, Nov 2021, Virtual, United Kingdom. ⟨hal-03541602⟩
126 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More