Takashi Nishide

4 papers · 2020–2024 · 4 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 🗺️ Taxonomy Completionist (13)

Venues

AAAI (1) ECCV (1) NeurIPS (1) WACV (1)

Top co-authors

Genki Osada (4) Tsubasa Takahashi (2) Budrul Ahsan (2) Makoto Shing (1) Revoti Prasad Bora (1)

Research topics

Deep Learning (3) Models (3) Artificial Intelligence (2) Machine Learning (2) Core AI (2) Core Methods (2) Computer Vision (1) Generation (1) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Optimization & Theory (1)

Keywords

out-of-distribution detection (2) generative model (2) normalizing flow (2) score matching (1) diffusion model (1) score-based diffusion model (1) stein identity (1) latent space (1) deep generative model (1) stein's identity (1) typical set (1) adversarial example detection (1) image complexity (1) likelihood assignment (1) image generation (1) jacobian trace (1) likelihood estimation (1) reconstruction error (1)

Papers

Local Curvature Smoothing with Stein's Identity for Efficient Score Matching NeurIPS 2024 Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detection AAAI 2024 Out-of-Distribution Detection With Reconstruction Error and Typicality-Based Penalty WACV 2023 Regularization with Latent Space Virtual Adversarial Training ECCV 2020