Jaehyun Pahk — accepted AI-conference papers

2025

Decoupled Finetuning for Domain Generalizable Semantic Segmentation

Jaehyun Pahk, Donghyeon Kwon, Seong Joon Oh, Suha Kwak

ICLR 2025poster

Joint finetuning of a pretrained encoder and a randomly initialized decoder has been the de facto standard in semantic segmentation, but the vulnerability of this approach to domain shift has not been studied. We investigate the vulnerability issue of joint finetuning, and propose a novel finetuning…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation

Namyup Kim, Taeyoung Son, Jaehyun Pahk, Cuiling Lan, Wenjun Zeng, Suha Kwak

ICRA 2023poster

Domain generalization for semantic segmentation is highly demanded in real applications, where a trained model is expected to work well in previously unseen domains. One challenge lies in the lack of data which could cover the diverse distributions of the possible unseen domains for training. In thi…

Cited by 27 Source ↗Scholar ↗