AI Paper Atlas

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

FedVLN: Privacy-Preserving Federated Vision-and-Language Navigation

Kaiwen Zhou, Xin Eric Wang

ECCV 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Vertical federated learning · 13 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 federated training (FedEnvdrop) instead of centralized trainingEnvdrop · R2R val-unseenSR: 44.5 -> 47.5Improved
add federated training (FedCLIP-ViL) instead of centralized trainingCLIP-ViL · R2R val-unseenSR: 53.6 -> 53.4No clear effect
add federated training instead of centralized trainingEnvdrop and CLIP-ViL · R2R/RxR val-seenSR: average 2.8% SR gapHurt
add federated training instead of centralized trainingEnvdrop · RxR val-unseenSR: 35.0 -> 34.4No clear effect
add augmented data to federated trainingFedEnvdrop · R2R val-unseenSR: 47.5 -> 51.3Improved
add augmented data to federated trainingFedCLIP-ViL · R2R val-unseenSR: 53.4 -> 56.9Improved
add federated speaker instead of centralized speaker for augmentationCLIP speaker · R2R val-unseenBLEU2: 30.2 -> 31.6Improved
add federated speaker instead of centralized speaker for augmentationCLIP speaker · R2R val-seenBLEU2: 33.5 -> 31.3Hurt
share only the language encoder instead of full model in federated pre-exploration (ablation)Envdrop · R2R unseen valSR: 62.4 -> 67.2Improved
share only the language encoder instead of full model in federated pre-exploration (ablation)CLIP-ViT · R2R unseen valSR: 65.8 -> 69.1Improved
add seen environments to federated language encoder pre-exploration (ablation)Envdrop · R2R unseen valSR: 67.2 -> 68.3Improved
add seen environments to federated language encoder pre-exploration (ablation)CLIP-ViT · R2R unseen valSR: 69.1 -> 69.5Improved

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