Pouya Samangouei

4 papers · 2017–2020 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 🚀 Conference Pioneer

Venues

ICLR (2) ECCV (1) ICCV (1)

Top co-authors

Rama Chellappa (2) Nathan Silberman (2) Ardavan Saeedi (2) Alon Daks (1) Liam Nakagawa (1) Yang Liu (1) Maya Kabkab (1) Israel Malkin (1) Patrick Maher (1) Larry S. Davis (1)

Research topics

Machine Learning (2) Artificial Intelligence (1) Computer Vision (1) Deep Learning (1) Core AI (1) Domain-Specific (1) Learning Types (1) Models (1) Optimization & Theory (1)

Keywords

binary classification (1) model evaluation (1) label noise (1) adversarial attack (1) generative model (1) adversarial defense (1) ground truth (1) annotator disagreement (1) perturbation detection (1) classifier protection (1)

Papers

Discrepancy Ratio: Evaluating Model Performance When Even Experts Disagree on the Truth ICLR 2020 Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models ICLR 2018 ExplainGAN: Model Explanation via Decision Boundary Crossing Transformations ECCV 2018 SSH: Single Stage Headless Face Detector ICCV 2017