Daun Jeong — accepted AI-conference papers

2025

S4M: Boosting Semi-Supervised Instance Segmentation with SAM

Heeji Yoon, Heeseong Shin, Eunbeen Hong, Hyunwook Choi, Hansang Cho, Daun Jeong +1

ICCV 2025poster

Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to unreliable pseudo-label quality stemming from limited label…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery

Hyungmin Kim, Sungho Suh, Daehwan Kim, Daun Jeong, Hansang Cho, Junmo Kim

ICCV 2023poster

Recent advances in deep learning have significantly improved the performance of various computer vision applications. However, discovering novel categories in an incremental learning scenario remains a challenging problem due to the lack of prior knowledge about the number and nature of new categori…

Cited by 17 PDF ↗code ↗Scholar ↗