ECCV 2024 accepted papers on Federated learning and privacy
21 of the 2,387 papers accepted at ECCV 2024 (0.9%) are on Federated learning and privacy, compared with 0.9% at ECCV 2022. They fall into 4 topics.
See ECCV 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Personalized and heterogeneous FL · 12 papers
- Towards Multi-modal Transformers in Federated Learning (27 citations)
- FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients (18 citations)
- Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching (17 citations)
- Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents (15 citations)
- Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection (14 citations)
- FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning (4 citations)
- PFedEdit: Personalized Federated Learning via Automated Model Editing (4 citations)
- Feature Diversification and Adaptation for Federated Domain Generalization (3 citations)
- Federated Learning with Local Openset Noisy Labels (3 citations)
- Local and Global Flatness for Federated Domain Generalization (3 citations)
- FedHARM: Harmonizing Model Architectural Diversity in Federated Learning (1 citation)
- FedHide: Federated Learning by Hiding in the Neighbors
Privacy attacks and secure learning · 6 papers
- Fisher Calibration for Backdoor-Robust Heterogeneous Federated Learning (8 citations)
- SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks (6 citations)
- Personalized Privacy Protection Mask Against Unauthorized Facial Recognition (5 citations)
- Learning a Dynamic Privacy-preserving Camera Robust to Inversion Attacks (4 citations)
- "Veil Privacy on Visual Data: Concealing Privacy for Humans, Unveiling for DNNs" (1 citation)
- Unveiling Privacy Risks in Stochastic Neural Networks Training: Effective Image Reconstruction from Gradients (1 citation)
