Feb. 13, 2024, 5:45 a.m. | Masoud Taghikhah Nishant Kumar Sini\v{s}a \v{S}egvi\'c Abouzar Eslami Stefan Gumhold

cs.LG updates on arXiv.org arxiv.org

Discriminative learning effectively predicts true object class for image classification. However, it often results in false positives for outliers, posing critical concerns in applications like autonomous driving and video surveillance systems. Previous attempts to address this challenge involved training image classifiers through contrastive learning using actual outlier data or synthesizing outliers for self-supervised learning. Furthermore, unsupervised generative modeling of inliers in pixel space has shown limited success for outlier detection. In this work, we introduce a quantile-based maximum likelihood objective …

applications autonomous autonomous driving challenge class classification classifiers concerns cs.cv cs.lg data detection driving false false positives image likelihood outlier outliers quantile surveillance systems through training true video video surveillance

Research Scholar (Technical Research)

@ Centre for the Governance of AI | Hybrid; Oxford, UK

HPC Engineer (x/f/m) - DACH

@ Meshcapade GmbH | Remote, Germany

Encounter Data Management Professional

@ Humana | Work at Home - Kentucky

Pre-sales Manager (Data, Analytics & AI)

@ Databricks | Stockholm, Sweden

Lecturer / Senior Lecturer - Medical Imaging

@ Central Queensland University | Mackay, QLD, AU

Intern - Research Engineer

@ Plus | Santa Clara, CA