Image Model Blocks

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.

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


Paper Code Results Date Stars


Task Papers Share
Denoising 18 15.00%
Pose Estimation 15 12.50%
Deblurring 6 5.00%
Image Restoration 6 5.00%
Super-Resolution 6 5.00%
Image Reconstruction 5 4.17%
6D Pose Estimation using RGB 4 3.33%
Object Detection 4 3.33%
Image Deblurring 3 2.50%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign