Tae‐Kyun Kim

Sequential Graph Convolutional Network for Active Learning

2021

We propose a novel pool-based Active Learning framework constructed on a sequential Graph Convolution Network (GCN). Each images feature from a pool of data represents a node in the graph and the edges encode their …

Generalist Multi-Class Anomaly Detection via Distillation to Two Heterogeneous Student Networks

2025 · arXiv (Cornell University)

Anomaly detection (AD) plays an important role in various real-world applications. Recent advancements in AD, however, are often biased towards industrial inspection, struggle to generalize to broader tasks like semantic anomaly detection and vice versa. …