paper-with-me

Papers

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

2022-06-17 · Aliaksandra Shysheya, John Bronskill, Massimiliano Patacchiola, Sebastian Nowozin, Richard E Turner

Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of data, and ii) communication efficient distributed training protocols. In this work, we develop FiLM Transfer (FiT) which fulfills these requirements in the image classification setting by combining ideas from transfer learning (fixed pretrained backbones and fine-tuned FiLM adapter layers) and meta-learning (automatically configured Naive Bayes classifiers and episodic training) to yield parameter efficient models with superior classification accuracy at low-shot. The resulting parameter efficiency is key for enabling few-shot learning, inexpensive model updates for personalization, and communication efficient federated learning. We experiment with FiT on a wide range of downstream datasets and show that it achieves better classification accuracy than the leading Big Transfer (BiT) algorithm at low-shot and achieves state-of-the art accuracy on the challenging VTAB-1k benchmark, with fewer than 1% of the updateable parameters. Finally, we demonstrate the parameter efficiency and superior accuracy of FiT in distributed low-shot applications including model personalization and federated learning where model update size is an important performance metric.

📄 PDF Abstract BibTeX arXiv:2206.08671

Code (1)

cambridge-mlg/fit 공식 구현 pytorch

Tasks

Federated LearningFew-Shot Learningimage-classificationImage ClassificationMeta-LearningTransfer Learning

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

FedBiCross: Personalized One-Shot Federated Learning on Medical Images

2026-01-05 · Yuexuan Xia, Yinghao Zhang, Yalin Liu, Hong-Ning Dai 외 arxiv

Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, making OSFL attractive for privacy-sensitive medical applications. Howeve…

Data-free Knowledge DistillationFederated Learning

Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning

2026-05-04 · Shihao Hou, Chikai Shang, Zhiheng Yang, Jiacheng Yang 외 arxiv

Personalized federated learning (PFL) with foundation models has emerged as a promising paradigm enabling clients to adapt to heterogeneous data distributions. However, real-world scenarios often face the co-occurrence o…

Personalized Federated Learning

Personalized Quantum Federated Learning for Privacy Image Classification

2024-10-03 · Jinjing Shi, Tian Chen, Shichao Zhang, Xuelong Li

Quantum federated learning has brought about the improvement of privacy image classification, while the lack of personality of the client model may contribute to the suboptimal of quantum federated learning. A personaliz…

ClassificationFederated Learningimage-classificationImage Classification+1

Parameterized Knowledge Transfer for Personalized Federated Learning

2021-11-04 · NeurIPS 2021 12 · Jie Zhang, Song Guo, Xiaosong Ma, Haozhao Wang 외

In recent years, personalized federated learning (pFL) has attracted increasing attention for its potential in dealing with statistical heterogeneity among clients. However, the state-of-the-art pFL methods rely on model…

Federated LearningPersonalized Federated LearningTransfer Learning

Personalized Federated Learning with Residual Fisher Information for Medical Image Segmentation

2026-03-16 · Meilu Zhu, Yuxing Li, Zhiwei Wang, Edmund Y. Lam arxiv

Federated learning enables multiple clients (institutions) to collaboratively train machine learning models without sharing their private data. To address the challenge of data heterogeneity across clients, personalized …

Personalized Federated LearningMedical Image Segmentation