PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
Classical federated learning (FL) enables training machine learning models without sharing
data for privacy preservation, but heterogeneous data characteristic degrades the …
data for privacy preservation, but heterogeneous data characteristic degrades the …
Continual Learning for Smart City: A Survey
With the digitization of modern cities, large data volumes and powerful computational
resources facilitate the rapid update of intelligent models deployed in smart cities. Continual …
resources facilitate the rapid update of intelligent models deployed in smart cities. Continual …
SLMFed: A stage-based and layer-wise mechanism for incremental federated learning to assist dynamic and ubiquitous IoT
Along with the vast application of Internet of Things (IoT) and the ever-growing concerns
about data protection, a novel type of learning, named incremental federated learning (IFL) …
about data protection, a novel type of learning, named incremental federated learning (IFL) …
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification
Lifelong person re-identification (LReID) suffers from the catastrophic forgetting problem
when learning from non-stationary data. Existing exemplar-based and knowledge distillation …
when learning from non-stationary data. Existing exemplar-based and knowledge distillation …
Towards data-efficient continuous learning for edge video analytics via smart caching
Continuous learning (CL) has recently been adopted into edge video analytics, gaining
huge success in maintaining high accuracy without constantly retraining DNN models by …
huge success in maintaining high accuracy without constantly retraining DNN models by …
[HTML][HTML] Federated Unsupervised Cluster-Contrastive learning for person Re-identification: A coarse-to-fine approach
Abstract Person Re-identification (ReID) has attracted considerable interests in recent years,
largely driven by the escalating demand for public safety measures. However, the …
largely driven by the escalating demand for public safety measures. However, the …
Diverse Representation Embedding for Lifelong Person Re-Identification
Lifelong Person Re-Identification (LReID) aims to continuously learn from successive data
streams, matching individuals across multiple cameras. The key challenge for LReID is how …
streams, matching individuals across multiple cameras. The key challenge for LReID is how …
Attribute recognition for person re-identification using federated learning at all-in-edge
The advancement in person re-identification using attribute recognition is constrained by the
increasingly strict data privacy standards since it necessitates the centralization of vast …
increasingly strict data privacy standards since it necessitates the centralization of vast …
Exemplar-Free Lifelong Person Re-identification via Prompt-Guided Adaptive Knowledge Consolidation
Lifelong person re-identification (LReID) refers to matching people across different cameras
given continuous data streams. The challenge of catastrophic forgetting of old knowledge …
given continuous data streams. The challenge of catastrophic forgetting of old knowledge …
Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure
With increasing concerns over data privacy and model copyrights, especially in the context
of collaborations between AI service providers and data owners, an innovative Sentinel …
of collaborations between AI service providers and data owners, an innovative Sentinel …