Usama Muneeb — accepted AI-conference papers

2024

Induced Model Matching: Restricted Models Help Train Full-Featured Models

NeurIPS 2024spotlight

We consider scenarios where a very accurate (often small) predictive model using restricted features is available when training a full-featured (often larger) model. This restricted model may be thought of as ``side-information'', and can come either from an auxiliary dataset or from the same datase…

Cited by 0 Source ↗PDF ↗Scholar ↗

2020

Robust and Computationally-Efficient Anomaly Detection Using Powers-Of-Two Networks

Usama Muneeb, Erdem Koyuncu, Yasaman Keshtkarjahromi, Hulya Seferoglu, Mehmet Fatih Erden, A. Enis Çetin

ICASSP 2020accepted

Robust and computationally efficient anomaly detection in videos is a problem in video surveillance systems. We propose a technique to increase robustness and reduce computational complexity in a Convolutional Neural Network (CNN) based anomaly detector that utilizes the optical flow information of…

Cited by 0 Source ↗Scholar ↗