Localizing Objects with Self-Supervised Transformers and no Labels

09/29/2021
by   Oriane Siméoni, et al.
5

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.

READ FULL TEXT

page 1

page 4

page 5

page 22

page 23

page 24

page 25

research
12/15/2022

Unsupervised Object Localization: Observing the Background to Discover Objects

Recent advances in self-supervised visual representation learning have p...
research
01/09/2023

Data Discovery using Natural Language Questions via a Self-Supervised Approach

Data discovery systems help users identify relevant data among large tab...
research
04/11/2023

MOST: Multiple Object localization with Self-supervised Transformers for object discovery

We tackle the challenging task of unsupervised object localization in th...
research
09/08/2023

Unsupervised Object Localization with Representer Point Selection

We propose a novel unsupervised object localization method that allows u...
research
03/28/2023

ASIC: Aligning Sparse in-the-wild Image Collections

We present a method for joint alignment of sparse in-the-wild image coll...
research
10/24/2022

Foreground Guidance and Multi-Layer Feature Fusion for Unsupervised Object Discovery with Transformers

Unsupervised object discovery (UOD) has recently shown encouraging progr...
research
10/21/2019

Object landmark discovery through unsupervised adaptation

This paper proposes a method to ease the unsupervised learning of object...

Please sign up or login with your details

Forgot password? Click here to reset