2 papers
cs.CV2026
GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection
Jiacong Liu, Shu Luo, Yikai Qin +3
Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in…
cs.CV2026
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…