4 papers
Robust Promptable Video Object Segmentation
Sohyun Lee, Yeho Gwon, Lukas Hoyer +3
The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in safety-critical domains. Thi…
Learned split-spectrum metalens for obstruction-free broadband imaging in the visible
Seungwoo Yoon, Dohyun Kang, Eunsue Choi +9
Obstructions such as raindrops, fences, or dust degrade captured images, especially when mechanical cleaning is infeasible. Conventional solutions to obstructions rely on a bulky c…
GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation
Sohyun Lee, Yeho Gwon, Lukas Hoyer +1
Improving robustness of the Segment Anything Model (SAM) to input degradations is critical for its deployment in high-stakes applications such as autonomous driving and robotics. O…
TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
Sohyun Lee, Nayeong Kim, Juwon Kang +2
This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing while preserving previously learned knowledg…