Search Results for author: Nurbek Tastan

Found 4 papers, 4 papers with code

Redefining Contributions: Shapley-Driven Federated Learning

1 code implementation • 1 Jun 2024 • Nurbek Tastan, Samar Fares, Toluwani Aremu, Samuel Horvath, Karthik Nandakumar

This paper proposes a novel contribution assessment method called ShapFed for fine-grained evaluation of participant contributions in FL.

Fairness Federated Learning

Paper
Code

Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline

1 code implementation • 1 Apr 2024 • Anas Al-lahham, Muhammad Zaigham Zaheer, Nurbek Tastan, Karthik Nandakumar

Unsupervised (US) video anomaly detection (VAD) in surveillance applications is gaining more popularity recently due to its practical real-world applications.

Anomaly Detection Privacy Preserving +1

Paper
Code

A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection

1 code implementation • 26 Oct 2023 • Anas Al-lahham, Nurbek Tastan, Zaigham Zaheer, Karthik Nandakumar

Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings.

One-Class Classification Pseudo Label +1

Paper
Code

CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss

1 code implementation • CVPR 2023 • Nurbek Tastan, Karthik Nandakumar

In CaPriDe learning, participating entities release their private data in an encrypted form allowing other participants to perform inference in the encrypted domain.

Federated Learning Knowledge Distillation

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.