Cover Image

Redefining non-IID Data in Federated Learning for Computer Vision Tasks: Migrating from Labels to Embeddings for Task-Specific Data Distributions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Borazjani, Kasra, Abdisarabshali, Payam, Khosravan, Naji, Hosseinalipour, Seyyedali
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Modal Federated Learning for Cancer Staging over Non-IID Datasets with Unbalanced Modalities
by: Borazjani, Kasra, et al.
Published: (2024)

Multi-Modal Multi-Task (M3T) Federated Foundation Models for Embodied AI: Potentials and Challenges for Edge Integration
by: Borazjani, Kasra, et al.
Published: (2025)

Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges
by: Borazjani, Kasra, et al.
Published: (2025)

Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR
by: Nadimi, Fardis, et al.
Published: (2025)

Hierarchical Federated Foundation Models over Wireless Networks for Multi-Modal Multi-Task Intelligence: Integration of Edge Learning with D2D/P2P-Enabled Fog Learning Architectures
by: Abdisarabshali, Payam, et al.
Published: (2025)

Elastic Federated Learning over Open Radio Access Network (O-RAN) for Concurrent Execution of Multiple Distributed Learning Tasks
by: Abdisarabshali, Payam, et al.
Published: (2023)

Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels
by: Wagle, Satyavrat, et al.
Published: (2024)

Deformable Capsules for Object Detection
by: Lalonde, Rodney, et al.
Published: (2021)

From Federated Learning to X-Learning: Breaking the Barriers of Decentrality Through Random Walks
by: Salihovic, Allan, et al.
Published: (2025)

Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data
by: Ardıç, Emre, et al.
Published: (2026)

Towards Robust Federated Learning via Logits Calibration on Non-IID Data
by: Qiao, Yu, et al.
Published: (2024)

Graph Theory Meets Federated Learning over Satellite Constellations: Spanning Aggregations, Network Formation, and Performance Optimization
by: Nadimi, Fardis, et al.
Published: (2025)

GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Task
by: Lu, Shiwei, et al.
Published: (2026)

D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement
by: Peng, Yansong, et al.
Published: (2024)

ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences
by: Zhu, Liyuan, et al.
Published: (2025)

Task-Specific Data Preparation for Deep Learning to Reconstruct Structures of Interest from Severely Truncated CBCT Data
by: Huang, Yixing, et al.
Published: (2024)

Dynamic D2D-Assisted Federated Learning over O-RAN: Performance Analysis, MAC Scheduler, and Asymmetric User Selection
by: Abdisarabshali, Payam, et al.
Published: (2024)

Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation
by: Liu, Chenying, et al.
Published: (2024)

Multidimensional Task Learning: A Unified Tensor Framework for Computer Vision Tasks
by: Ichi, Alaa El, et al.
Published: (2026)

Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data
by: Qiao, Yu, et al.
Published: (2024)

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
by: Gangwar, Neeraj, et al.
Published: (2025)

Adaptive Dual-Mode Distillation with Incentive Schemes for Scalable, Heterogeneous Federated Learning on Non-IID Data
by: Iqbal, Zahid
Published: (2025)

FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Data
by: Zhao, Yushan, et al.
Published: (2025)

Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies
by: Sarkar, Ayushman, et al.
Published: (2025)

FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification
by: Tsai, Cheng-Chang, et al.
Published: (2025)

Learning What Helps: Task-Aligned Context Selection for Vision Tasks
by: Guo, Jingyu, et al.
Published: (2025)

LVLM-Aided Alignment of Task-Specific Vision Models
by: Koebler, Alexander, et al.
Published: (2025)

Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks
by: Dushenev, Daniil, et al.
Published: (2026)

Task-Aware Scanning Parameter Configuration for Robotic Inspection Using Vision Language Embeddings and Hyperdimensional Computing
by: Chen, Zhiling, et al.
Published: (2026)

Federated Learning with Partially Labeled Data: A Conditional Distillation Approach
by: Wang, Pochuan, et al.
Published: (2024)

SGW-based Multi-Task Learning in Vision Tasks
by: Zhang, Ruiyuan, et al.
Published: (2024)

Data Stream Sampling with Fuzzy Task Boundaries and Noisy Labels
by: Chen, Yu-Hsi
Published: (2024)

Multi-Task Learning for Robot Perception with Imbalanced Data
by: Erkent, Ozgur
Published: (2026)

Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships
by: Daroya, Rangel, et al.
Published: (2024)

Olympus: A Universal Task Router for Computer Vision Tasks
by: Lin, Yuanze, et al.
Published: (2024)

FedBrain-Distill: Communication-Efficient Federated Brain Tumor Classification Using Ensemble Knowledge Distillation on Non-IID Data
by: Gohari, Rasoul Jafari, et al.
Published: (2024)

Joint-Task Regularization for Partially Labeled Multi-Task Learning
by: Nishi, Kento, et al.
Published: (2024)

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning
by: Xu, Zhiyang, et al.
Published: (2024)

AnyRefill: A Unified, Data-Efficient Framework for Left-Prompt-Guided Vision Tasks
by: Xie, Ming, et al.
Published: (2025)

AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks
by: Li, You, et al.
Published: (2024)