FORLA: Federated Object-centric Representation Learning with Slot Attention

TL;DR

FORLA introduces a federated learning framework that uses unsupervised slot attention to learn object-centric visual representations across diverse, unlabeled datasets, enabling effective cross-domain feature adaptation and improved object discovery.

Contribution

The paper presents FORLA, a novel federated object-centric learning framework utilizing shared slot attention and a student-teacher architecture for unsupervised cross-client feature adaptation.

Findings

Outperforms centralized baselines on object discovery tasks.

Learns a compact, universal representation that generalizes across domains.

Demonstrates effective unsupervised visual representation learning in federated settings.

Abstract

Learning efficient visual representations across heterogeneous unlabeled datasets remains a central challenge in federated learning. Effective federated representations require features that are jointly informative across clients while disentangling domain-specific factors without supervision. We introduce FORLA, a novel framework for federated object-centric representation learning and feature adaptation across clients using unsupervised slot attention. At the core of our method is a shared feature adapter, trained collaboratively across clients to adapt features from foundation models, and a shared slot attention module that learns to reconstruct the adapted features. To optimize this adapter, we design a two-branch student-teacher architecture. In each client, a student decoder learns to reconstruct full features from foundation models, while a teacher decoder reconstructs their adapted, low-dimensional counterpart. The shared slot attention module bridges cross-domain learning by aligning object-level representations across clients. Experiments in multiple real-world datasets show that our framework not only outperforms centralized baselines on object discovery but also learns a compact, universal representation that generalizes well across domains. This work highlights federated slot attention as an effective tool for scalable, unsupervised visual representation learning from cross-domain data with distributed concepts.