Author

Hoseok Do

h-index 5 View on Semantic Scholar

We have 1 of 11 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation

This work proposes a hybrid pipeline coupling T2I generation with context-aware image-to-image (I2I) editing, and introduces VRAIN (Verified Rare-class Augmentation via INstructed editing), a novel I2I editor to strengthen supervision for rare classes.

H. Song, Seokhun Choi, Hoseok Do · 0 citations