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

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Denoising 10 27.78%
Pose Estimation 4 11.11%
Object Detection 3 8.33%
Pose Tracking 1 2.78%
Autonomous Driving 1 2.78%
Depth Estimation 1 2.78%
Motion Estimation 1 2.78%
3D Object Detection 1 2.78%
6D Pose Estimation using RGB 1 2.78%

Components


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

Categories