1 citations · 2 across the 4 of their papers we have counts for
5 papers
Anomaly Detection by Effectively Leveraging Synthetic Images
Sungho Kang, Hyunkyu Park, Yeonho Lee +5
Anomaly detection plays a vital role in industrial manufacturing. Due to the scarcity of real defect images, unsupervised approaches that rely solely on normal images have been ext…
Few-Shot Class-Incremental Model Attribution Using Learnable Representation From CLIP-ViT Features
Hanbyul Lee, Juneho Yi
Recently, images that distort or fabricate facts using generative models have become a social concern. To cope with continuous evolution of generative artificial intelligence (AI)…
Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detection
YeongHyeon Park, Sungho Kang, Myung Jin Kim +2
In unsupervised anomaly detection (UAD) research, while state-of-the-art models have reached a saturation point with extensive studies on public benchmark datasets, they adopt larg…
Scene Depth Estimation from Traditional Oriental Landscape Paintings
Sungho Kang, YeongHyeon Park, Hyunkyu Park +1
Scene depth estimation from paintings can streamline the process of 3D sculpture creation so that visually impaired people appreciate the paintings with tactile sense. However, mea…
Excision And Recovery: Visual Defect Obfuscation Based Self-Supervised Anomaly Detection Strategy
YeongHyeon Park, Sungho Kang, Myung Jin Kim +3
Due to scarcity of anomaly situations in the early manufacturing stage, an unsupervised anomaly detection (UAD) approach is widely adopted which only uses normal samples for traini…