4 papers
Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
Jinhyeok Jang, Jaehong Kim, Jung Uk Kim
Pre-trained weights have become a cornerstone of modern deep learning, enabling efficient knowledge transfer and improving downstream task performance, especially in data-scarce sc…
Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data
Youngmin Oh, Hyung-Il Kim, Jung Uk Kim
Multi-task learning (MTL) is critical in real-world applications such as autonomous driving and robotics, enabling simultaneous handling of diverse tasks. However, obtaining fully…
Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation
Taeyeong Kim, SeungJoon Lee, Jung Uk Kim +1
Domain generalization in semantic segmentation faces challenges from domain shifts, particularly under adverse conditions. While diffusion-based data generation methods show promis…
Multispectral Pedestrian Detection with Sparsely Annotated Label
Chan Lee, Seungho Shin, Gyeong-Moon Park +1
Although existing Sparsely Annotated Object Detection (SAOD) approches have made progress in handling sparsely annotated environments in multispectral domain, where only some pedes…