A malicious FL server can steal private training images by encoding them into model parameters via a correlation regularizer and preserving them through segmented aggregation.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
HieDG discretizes geometric cues with a hierarchical residual codebook and integrates the resulting tokens into query-based trackers to boost identity consistency on animal and generic MOT benchmarks.
Pre-training on modality-matched data significantly improves downstream performance in medical imaging models while self-supervised learning benefits depend on context.
citing papers explorer
-
FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation
A malicious FL server can steal private training images by encoding them into model parameters via a correlation regularizer and preserving them through segmented aggregation.
-
HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking
HieDG discretizes geometric cues with a hierarchical residual codebook and integrates the resulting tokens into query-based trackers to boost identity consistency on animal and generic MOT benchmarks.
-
From pre-training to downstream performance: Does domain-specific pre-training make sense?
Pre-training on modality-matched data significantly improves downstream performance in medical imaging models while self-supervised learning benefits depend on context.