Unsupervised object localization: Observing the background to discover objects

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F23%3A00367553" target="_blank" >RIV/68407700:21730/23:00367553 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/CVPR52729.2023.00310" target="_blank" >https://doi.org/10.1109/CVPR52729.2023.00310</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52729.2023.00310" target="_blank" >10.1109/CVPR52729.2023.00310</a>

Result language

angličtina

Original language name

Unsupervised object localization: Observing the background to discover objects

Original language description

Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is a very hard task; what are the desired objects, when to separate them into parts, how many are there, and of what classes? The answers to these questions depend on the tasks and datasets of evaluation. In this work, we take a different approach and propose to look for the background instead. This way, the salient objects emerge as a by-product without any strong assumption on what an object should be. We propose FOUND, a simple model made of a single conv 1x1 initialized with coarse background masks extracted from self-supervised patch-based representations. After fast training and refining these seed masks, the model reaches state-of-the-art results on unsupervised saliency detection and object discovery benchmarks. Moreover, we show that our approach yields good results in the unsupervised semantic segmentation retrieval task. The code to reproduce our results is available at https://github. com/valeoai/FOUND.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

979-8-3503-0129-8

ISSN

1063-6919

e-ISSN

2575-7075

Number of pages

11

Pages from-to

3176-3186

Publisher name

IEEE Computer Society

Place of publication

USA

Event location

Vancouver

Event date

Jun 18, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001058542603045