PnP

2000년 도입 · 논문 114편에서 사용

PnP, or Poll and Pool, is sampling module extension for DETR-type architectures that adaptively allocates its computation spatially to be more efficient. Concretely, the PnP module abstracts the image feature map into fine foreground object feature vectors and a small number of coarse background contextual feature vectors. The transformer models information interaction within the fine-coarse feature space and translates the features into the detection result.

출처: PnP-DETR: Towards Efficient Visual Analysis with Transformers

소개 논문: PnP-DETR: Towards Efficient Visual Analysis with Transformers