Jae-Gil Lee

Full Professor, Korea Advanced Institute of Science and Technology

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation

#116 · Byunghyun Kim, Minyoung Bae, Jae-Gil Lee

A sample-efficient diffusion-based data augmentation method for instance segmentation, achieved by multi-round copy-paste augmentation with model feedback.