AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation

Jiaxu Miao, Zongxin Yang, Leilei Fan, Yi Yang

CVPR 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 70 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add background-classes aggregation cross-entropy (ablation)FedAvg semantic segmentation · Cityscapes non-IID1mIoU: 10.40 -> 45.08Improved
Add background-classes aggregation cross-entropy (ablation)FedAvg semantic segmentation · CamVID non-IID1mIoU: 19.06 -> 58.38Improved
Add background-classes aggregation cross-entropy (ablation)FedAvg semantic segmentation · PascalVOCmIoU: 8.56 -> 32.28Improved
Add local-to-global pixel contrastive loss (ablation)FedAvg + Lbackce · Cityscapes non-IID1mIoU: 45.08 -> 50.24Improved
Add local-to-global pixel contrastive loss (ablation)FedAvg + Lbackce · CamVID non-IID1mIoU: 58.38 -> 63.50Improved
Add local-to-global pixel contrastive loss (ablation)FedAvg + Lbackce · PascalVOCmIoU: 32.28 -> 32.20Hurt
Add local-to-global pixel contrastive loss (ablation)FedAvg + Lbackce · ADE20kmIoU: 8.31 -> 8.64Improved
Replace local-to-local pixel contrastive learning with local-to-global contrastive learning (ablation)FedSeg · Cityscapes non-IID1mIoU: 47.91% -> 50.24%Improved
Use pixel-to-region rather than pixel-to-pixel contrastive sampling (ablation)FedSeg · Cityscapes non-IID1mIoU: 49.95% -> 50.24%No clear effect
Increase the number of local epochs per round (ablation)FedSeg · Cityscapes non-IID1 and CamVID non-IID1mIoUHurt

Later papers that compared with this method

1 later accepted paper reports FedSeg as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy