Related papers: FORLA: Federated Object-centric Representation Lea…

Federated Learning (FL) aims to learn a single global model that enables the central server to help the model training in local clients without accessing their local data. The key challenge of FL is the heterogeneity of local data in…

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not…

To leverage enormous unlabeled data on distributed edge devices, we formulate a new problem in federated learning called Federated Unsupervised Representation Learning (FURL) to learn a common representation model without supervision while…

Vision-Language-Action (VLA) models hold great promise for general-purpose robotic intelligence, yet scaling up such models is severely bottlenecked by the high cost of acquiring annotated training data. Fortunately, vision-equipped robots…

Federated learning (FL) is a distributed learning framework that leverages commonalities between distributed client datasets to train a global model. Under heterogeneous clients, however, FL can fail to produce stable training results.…

Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vectors, called slots. Current methods obtain these slot…

In the pursuit of refining precise perception models for fully autonomous driving, continual online model training becomes essential. Federated Learning (FL) within vehicular networks offers an efficient mechanism for model training while…

Slot Attention (SA) with pretrained diffusion models has recently shown promise for object-centric learning (OCL), but suffers from slot entanglement and weak alignment between object slots and image content. We propose Contrastive…

Prototype-based federated learning has emerged as a promising approach that shares lightweight prototypes to transfer knowledge among clients with data heterogeneity in a model-agnostic manner. However, existing methods often collect…

A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…

Personalized Federated Learning (PFL) faces persistent challenges, including domain heterogeneity from diverse client data, data imbalance due to skewed participation, and strict communication constraints. Traditional federated learning…

Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure is implicitly…

Effectively leveraging private datasets remains a significant challenge in developing foundation models. Federated Learning (FL) has recently emerged as a collaborative framework that enables multiple users to fine-tune these models while…

Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot…

The extraction of modular object-centric representations for downstream tasks is an emerging area of research. Learning grounded representations of objects that are guaranteed to be stable and invariant promises robust performance across…

Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning. Recently, techniques for unsupervised learning of object-centric representations have raised growing interest. In…

Federated learning has been predominantly concerned with collaborative training of deep networks from scratch, and especially the many challenges that arise, such as communication cost, robustness to heterogeneous data, and support for…

The federated learning (FL) framework enables edge clients to collaboratively learn a shared inference model while keeping privacy of training data on clients. Recently, many heuristics efforts have been made to generalize centralized…

Federated learning (FL) enables collaborative training across distributed clients without sharing raw data, often at the cost of substantial communication overhead induced by transmitting high-dimensional model updates. This overhead can be…

Learning object-level, structured representations is widely regarded as a key to better generalization in vision and underpins the design of next-generation Pre-trained Vision Models (PVMs). Mainstream Object-Centric Learning (OCL) methods…