Description
The Contour Proposal Network (CPN) detects possibly overlapping objects in an image while simultaneously fitting pixel-precise closed object contours. The CPN can incorporate state of the art object detection architectures as backbone networks into a fast single-stage instance segmentation model that can be trained end-to-end.
Papers Using This Method
Colored Petri Nets for Modeling and Simulation of a Green Supply Chain System2024-06-07CPN: Complementary Proposal Network for Unconstrained Text Detection2024-02-18Formal Translation from Reversing Petri Nets to Coloured Petri Nets2023-11-01Double-chain Constraints for 3D Human Pose Estimation in Images and Videos2023-08-10ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention2023-04-04Uncertainty-Aware Contour Proposal Networks for Cell Segmentation in Multi-Modality High-Resolution Microscopy Images2022-11-30SLAMs: Semantic Learning based Activation Map for Weakly Supervised Semantic Segmentation2022-10-22Contrastive Prototypical Network with Wasserstein Confidence Penalty2022-10-21P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation2022-03-15Visual Goal-Directed Meta-Learning with Contextual Planning Networks2021-11-18Complementary Patch for Weakly Supervised Semantic Segmentation2021-08-09Acyclic and Cyclic Reversing Computations in Petri Nets2021-08-04Cascaded Prediction Network via Segment Tree for Temporal Video Grounding2021-06-19Contour Proposal Networks for Biomedical Instance Segmentation2021-04-07