Jungwook Seo
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Vision×2AI×2
Frequent co-authors
Research Timeline
2026
BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers
BiasEdit introduces a training-free framework that automatically detects and edits unknown social biases in web-sourced image datasets to construct a debiased dataset for fair visual classification.
Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
The paper proposes ANoCo, a training-free method that detects visual anomalies by quantifying how much a query patch deviates from the structure of a fixed normal feature manifold using graph Laplacian energy minimization.
Highlighted terms show continued research focus across papers
Papers
cs.CVcs.AIRecentMay 27, 2026
BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers
BiasEdit introduces a training-free framework that automatically detects and edits unknown social biases in web-sourced image datasets to construct a debiased dataset for fair visual classification.
View →
cs.CVcs.AIRecentMay 27, 2026