Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey

Oriane Siméoni    Éloi Zablocki    Spyros Gidaris    Gilles Puy    Patrick Pérez

IJCV 2024

Paper   Code   

project teaser

Abstract

The recent enthusiasm for open-world vision systems show the high interest of the community to perform perception tasks outside of the closed-vocabulary benchmark setups which have been so popular until now. Being able to discover objects in images/videos without knowing in advance what objects populate the dataset is an exciting prospect. But how to find objects without knowing anything about them? Recent works show that it is possible to perform class-agnostic unsupervised object localization by exploiting self-supervised pre-trained features. We propose here a survey of unsupervised object localization methods that discover objects in images without requiring any manual annotation in the era of self-supervised ViTs.



BibTeX

@inproceedings{simeoni2024unsup_obj_loc_survey,
    title = {Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey},
    author = {Oriane Sim\'eoni and
              {\'{E}}loi Zablocki and
              Spyros Gidaris and
              Gilles Puy and
              Patrick P\'erez},
    booktitle = {IJCV},
    year      = {2024}
}