Jan 21, 2026 · Artificial Intelligence

Introducing ICONIC-444: A 3.1M Industrial Image Dataset Redefining OOD Detection

The article presents ICONIC-444, a 3.1‑million‑image, 444‑class industrial dataset designed for out‑of‑distribution (OOD) detection, explains its realistic acquisition process, hierarchical OOD categories, benchmark tasks, and evaluates 22 state‑of‑the‑art OOD methods, revealing how dataset characteristics influence algorithm performance.

AI SafetyICONIC-444OOD detection

0 likes · 10 min read

Introducing ICONIC-444: A 3.1M Industrial Image Dataset Redefining OOD Detection

Alimama Tech

Sep 11, 2024 · Artificial Intelligence

A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective

The paper introduces a coupled generative adversarial framework that merges biased observational with unbiased experimental data to create a bias‑free dataset for causal inference, enabling robust treatment‑effect estimation under collider bias from an out‑of‑distribution perspective, and demonstrates superior bias reduction on three public advertising datasets.

Generative Adversarial Networkscausal inferenceincremental value

0 likes · 10 min read

A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective