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

Oriane Siméoni, Éloi Zablocki, Spyros Gidaris, Gilles Puy, Patrick Pérez
10/19/2023
cs.CV

Official code: valeoai/Awesome-Unsupervised-Object-Localization (74 stars, Apache-2.0, last commit 2024-08-19).

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. We gather links of discussed methods in the repository https://github.com/valeoai/Awesome-Unsupervised-Object-Localization.

View on arXivView PDF

Code Implementations(1)

Apache-2.0

Curated list of awesome works on unsupervised object localization in 2D images.

743Oct 16, 20232 years agoApache-2.0

Similar Papers

Cite this paper

@article{simoni2023unsupervised,
  title  = {Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey},
  author = {Oriane Siméoni and Éloi Zablocki and Spyros Gidaris and Gilles Puy and Patrick Pérez},
  year   = {2023},
  eprint = {2310.12904},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.12904v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.12904.svg)](https://codeofpaper.com/paper/2310.12904)

Discussion