Fine-tuning visual models has been widely shown promising performance on many
downstream visual tasks. With the surprising development of pre-trained visual foundation …

Continual learning (CL) aims to incrementally learn different tasks (such as classification) in
a non-stationary data stream without forgetting old ones. Most CL works focus on tackling …

Foundation models (FMs) adapt surprisingly well to downstream tasks with fine-tuning.
However, their colossal parameter space prohibits their training on resource-constrained …

Few-shot classification consists of a training phase where a model is learned on a relatively
large dataset and an adaptation phase where the learned model is adapted to previously …

Federated learning (FL) emerges as a decentralized learning framework which trains
models from multiple distributed clients without sharing their data to preserve privacy …

Abstract In Class-Incremental Learning (CIL) an image classification system is exposed to
new classes in each learning session and must be updated incrementally. Methods …

Federated Learning (FL) is an emerging paradigm that allows a model to be trained across a
number of participants without sharing data. Recent works have begun to consider the …

Abstract Personalized Federated Learning (pFL) has emerged as a promising solution to
tackle data heterogeneity across clients in FL. However existing pFL methods either (1) …

Despite deep learning's widespread success, its data-hungry and computationally
expensive nature makes it impractical for many data-constrained real-world applications …

There has been significant recent progress in training differentially private (DP) models
which achieve accuracy that approaches the best non-private models. These DP models are …