4 papers
Towards Continual Expansion of Data Coverage: Automatic Text-guided Edge-case Synthesis
Kyeongryeol Go
The performance of deep neural networks is strongly influenced by the quality of their training data. However, mitigating dataset bias by manually curating challenging edge cases r…
The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
Xingyu Qiu, Yuqian Fu, Jiawei Geng +70
Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across…
ZERO: Industry-ready Vision Foundation Model with Multi-modal Prompts
Sangbum Choi, Kyeongryeol Go, Taewoong Jang
Foundation models have revolutionized AI, yet they struggle with zero-shot deployment in real-world industrial settings due to a lack of high-quality, domain-specific datasets. To…
Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective
Seunghyeon Kim, Kyeongryeol Go
Fisheye cameras introduce significant distortion and pose unique challenges to object detection models trained on conventional datasets. In this work, we propose a data-centric pip…