Yedid Hoshen

VAIN: Attentional Multi-agent Predictive Modeling

2017 · arXiv (Cornell University)

Multi-agent predictive modeling is an essential step for understanding physical, social and team-play systems. Recently, Interaction Networks (INs) were proposed for the task of modeling multi-agent physical systems, INs scale with the number of interactions …

Mean-Shifted Contrastive Loss for Anomaly Detection

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Deep anomaly detection methods learn representations that separate between normal and anomalous images. Although self-supervised representation learning is commonly used, small dataset sizes limit its effectiveness. It was previously shown that utilizing external, generic datasets …

Time Series Anomaly Detection by Cumulative Radon Features

2022 · arXiv (Cornell University)

Detecting anomalous time series is key for scientific, medical and industrial tasks, but is challenging due to its inherent unsupervised nature. In recent years, progress has been made on this task by learning increasingly more …

No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detection

2023 · arXiv (Cornell University)

Anomaly detection methods, powered by deep learning, have recently been making significant progress, mostly due to improved representations. It is tempting to hypothesize that anomaly detection can improve indefinitely by increasing the scale of our …