AINeutralarXiv – CS AI · 18h ago5/10
🧠
Proposal Refinement for Few-Shot Object Detection
Researchers propose a proposal refinement approach for few-shot object detection that addresses the unbalanced distribution of region proposals between novel and base classes. The method introduces a refinement loss during base training and a refinement branch for RPN during fine-tuning, achieving 1-6% performance improvements on benchmarks without additional inference costs.