Research map / Federated learning and privacy / Personalized and heterogeneous FL
FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity
Ganghyeon Lee, inha Lee, Junhee Lee, Jeongeon Lee, Sung Whan Yoon, Kyungdon Joo
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use soft instead of hard clustering (ablation) | FeDepth · M3ED HPE (NeWCRFs) | Abs Rel: 0.264 -> 0.249 | Improved |
| raise cluster overlap from 0% to 20% (ablation) | FeDepth · M3ED HPE (NeWCRFs) | Abs Rel: 0.335 -> 0.249 | Improved |
| raise cluster overlap from 20% to 50% (ablation) | FeDepth · M3ED HPE (NeWCRFs) | Abs Rel: 0.249 -> 0.300 | Hurt |
| 100% overlap (single cluster) (ablation) | FeDepth · M3ED HPE (NeWCRFs) | Abs Rel: 0.365 vs FedAvg 0.366 | Hurt |
| use descriptor-based clusters instead of ground-truth platform/environment label clusters (ablation) | FeDepth · M3ED HPE (NeWCRFs) | Abs Rel: 0.249 vs 0.471 (UGV only) | Improved |
| FeDepth vs FedAvg on AdaBins | FeDepth · M3ED HPE | Abs Rel: 0.434 -> 0.318 | Improved |
| FeDepth vs FedAvg on NeWCRFs | FeDepth · M3ED HPE | Abs Rel: 0.366 -> 0.249 | Improved |
| FeDepth vs FedAvg on DCDepth | FeDepth · M3ED HPE | Abs Rel: 0.351 -> 0.293 | Improved |
| FeDepth vs hard-clustering PACFL on BMR with AdaBins | FeDepth · BMR | Abs Rel: 0.124 vs 0.126 | No clear effect |
| FeDepth vs PACFL on BMR with NeWCRFs | FeDepth · BMR | Abs Rel: 0.087 vs 0.089 | No clear effect |
| hard clustering PACFL with descriptor extractor on HPE AdaBins | PACFL · M3ED HPE (AdaBins) | Abs Rel: 0.434 -> 0.602 | Hurt |
| pFedMe global model vs FeDepth | pFedMe · M3ED HPE (NeWCRFs) | Abs Rel: 0.563 vs 0.249 | Hurt |
Closest papers by meaning
- FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning (AAAI 2024 · similarity 0.86)
- Enhancing Foundation Models with Federated Domain Knowledge Infusion (ICML 2025 · similarity 0.85)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.85)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.84)
- F^3OCUS - Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics (CVPR 2025 · similarity 0.84)
- Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers (NeurIPS 2024 · similarity 0.84)
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.
