CTRL-O: Language-Controllable Object-Centric Visual Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Didolkar, Aniket, Zadaianchuk, Andrii, Awal, Rabiul, Seitzer, Maximilian, Gavves, Efstratios, Agrawal, Aishwarya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913762748923904
author Didolkar, Aniket
Zadaianchuk, Andrii
Awal, Rabiul
Seitzer, Maximilian
Gavves, Efstratios
Agrawal, Aishwarya
author_facet Didolkar, Aniket
Zadaianchuk, Andrii
Awal, Rabiul
Seitzer, Maximilian
Gavves, Efstratios
Agrawal, Aishwarya
contents Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown remarkable success in object discovery in diverse domains, including complex real-world scenes. However, these models suffer from a key limitation: they lack controllability. Specifically, current object-centric models learn representations based on their preconceived understanding of objects, without allowing user input to guide which objects are represented. Introducing controllability into object-centric models could unlock a range of useful capabilities, such as the ability to extract instance-specific representations from a scene. In this work, we propose a novel approach for user-directed control over slot representations by conditioning slots on language descriptions. The proposed ConTRoLlable Object-centric representation learning approach, which we term CTRL-O, achieves targeted object-language binding in complex real-world scenes without requiring mask supervision. Next, we apply these controllable slot representations on two downstream vision language tasks: text-to-image generation and visual question answering. The proposed approach enables instance-specific text-to-image generation and also achieves strong performance on visual question answering.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CTRL-O: Language-Controllable Object-Centric Visual Representation Learning
Didolkar, Aniket
Zadaianchuk, Andrii
Awal, Rabiul
Seitzer, Maximilian
Gavves, Efstratios
Agrawal, Aishwarya
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown remarkable success in object discovery in diverse domains, including complex real-world scenes. However, these models suffer from a key limitation: they lack controllability. Specifically, current object-centric models learn representations based on their preconceived understanding of objects, without allowing user input to guide which objects are represented. Introducing controllability into object-centric models could unlock a range of useful capabilities, such as the ability to extract instance-specific representations from a scene. In this work, we propose a novel approach for user-directed control over slot representations by conditioning slots on language descriptions. The proposed ConTRoLlable Object-centric representation learning approach, which we term CTRL-O, achieves targeted object-language binding in complex real-world scenes without requiring mask supervision. Next, we apply these controllable slot representations on two downstream vision language tasks: text-to-image generation and visual question answering. The proposed approach enables instance-specific text-to-image generation and also achieves strong performance on visual question answering.
title CTRL-O: Language-Controllable Object-Centric Visual Representation Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2503.21747